AI Detector Zero Chatgpt

AI Detector Zero Chatgpt — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Logistics automation

Logistics automation is the application of computer software or automated machinery to logistics operations in order to improve its efficiency. Typically this refers to operations within a warehouse or distribution center, with broader tasks undertaken by supply chain engineering systems and enterprise resource planning systems. Logistics automation systems can powerfully complement the facilities provided by these higher level computer systems. The focus on an individual node within a wider logistics network allows systems to be highly tailored to the requirements of that node. == Components == Logistics automation systems comprise a variety of hardware and software components: Fixed machinery Automated storage and retrieval systems, including: Cranes serve a rack of locations, allowing many levels of stock to be stacked vertically, and allowing for higher storage densities and better space utilization than alternatives. In systems produced by Amazon Robotics, automated guided vehicles move items to a human picker. Conveyors: Containers can enter automated conveyors in one area of the warehouse and, either through hard-coded rules or data input, be moved to a selected destination. Vertical carousels based on the paternoster lift system or using space optimization, similar to vending machines, but on a larger scale. Sortation systems: similar to conveyors but typically with higher capacity and able to divert containers more quickly. Typically used to distribute high volumes of small cartons to a large set of locations. Industrial robots: four- to six-axis industrial robots, e.g. palletizing robots, are used for palletizing, depalletizing, packaging, commissioning and order picking. Typically all of these will automatically identify and track containers using barcodes or, increasingly, RFID tags. Motion check weighers may be used to reject cases or individual products that are under or over their specified weight. They are often used in kitting conveyor lines to ensure all pieces belonging in the kit are present. Mobile technology Radio data terminals: these are handheld or truck-mounted terminals which connect by radio to logistics automation software and provide instructions to operators moving throughout the warehouse. Many also have barcode scanners to allow identification of containers more quickly and accurately than manual keyboard entry. Software Integration software: this provides overall control of the automation machinery and allows cranes to be connected to conveyors for seamless stock movements. Operational control software: provides low-level decision-making, such as where to store incoming containers, and where to retrieve them when requested. Business control software: provides higher-level functionality, such as identification of incoming deliveries/stock, scheduling order fulfillment, and assignment of stock to outgoing trailers. == Benefits == A typical warehouse or distribution center will receive stock of a variety of products from suppliers and store these until the receipt of orders from customers, whether individual buyers (e.g. mail order), retail branches (e.g. chain stores), or other companies (e.g. wholesalers). A logistics automation system may provide the following: Automated goods in processes: Incoming goods can be marked with barcodes and the automation system notified of the expected stock. On arrival, the goods can be scanned and thereby identified, and taken via conveyors, sortation systems, and automated cranes into an automatically assigned storage location. Automated goods retrieval for orders: On receipt of orders, the automation system is able to immediately locate goods and retrieve them to a pick-face location. Automated dispatch processing: Combining knowledge of all orders placed at the warehouse the automation system can assign picked goods into dispatch units and then into outbound loads. Sortation systems and conveyors can then move these onto the outgoing trailers. If needed, repackaging to ensure proper protection for further distribution or to change the package format for specific retailers/customers. A complete warehouse automation system can drastically reduce the workforce required to run a facility, with human input required only for a few tasks, such as picking units of product from a bulk packed case. Even here, assistance can be provided with equipment such as pick-to-light units. Smaller systems may only be required to handle part of the process. Examples include automated storage and retrieval systems, which simply use cranes to store and retrieve identified cases or pallets, typically into a high-bay storage system which would be unfeasible to access using fork-lift trucks or any other means. The use of Automatic Guided Vehicles maximizes the output compared to humans since they can do repetitive tasks for long hours and with least to no supervision. An AGV is built and programmed for precision and accuracy thereby reducing the chances of errors in a warehouse, especially when dealing with fragile goods. == Automation software == Software or cloud-based SaaS solutions are used for logistics automation which helps the supply chain industry in automating the workflow as well as management of the system. Knowledge @ Wharton staff writers noted in 2011 that some manufacturers and retailers were weathering the Great Recession "by signing up for pay-as-you-go logistics services available through the Internet 'cloud'". They identified the benefits and reduced costs which came from sharing information about shipments with suppliers, hauliers and end users. There is little generalized software available in this market. This is because there is no rule to generalize the system as well as work flow even though the practice is more or less the same. Most of the commercial companies do use one or the other of the custom solutions. But there are various software solutions that are being used within the departments of logistics. There are a few departments in Logistics, namely: Conventional Department, Container Department, Warehouse, Marine Engineering, Heavy Haulage, etc. Software used in these departments Conventional department : CVT software / CTMS software. Container Trucking: CTMS software Warehouse : WMS/WCS Improving Effectiveness of Logistics Management Logistical Network Information Transportation Sound Inventory Management Warehousing, Materials Handling & Packaging
Read more →
MarkLogic Server

MarkLogic Server is a document-oriented database developed by MarkLogic. It is a NoSQL multi-model database that evolved from an XML database to natively store JSON documents and RDF triples, the data model for semantics. MarkLogic is designed to be a data hub for operational and analytical data. == History == MarkLogic Server was built to address shortcomings with existing search and data products. The product first focused on using XML as the document markup standard and XQuery as the query standard for accessing collections of documents up to hundreds of terabytes in size. Currently the MarkLogic platform is widely used in publishing, government, finance and other sectors. MarkLogic's customers are mostly Global 2000 companies. == Technology == MarkLogic uses documents without upfront schemas to maintain a flexible data model. In addition to having a flexible data model, MarkLogic uses a distributed, scale-out architecture that can handle hundreds of billions of documents and hundreds of terabytes of data. It has received Common Criteria certification, and has high availability and disaster recovery. MarkLogic is designed to run on-premises and within public or private cloud environments like Amazon Web Services. == Features == Indexing MarkLogic indexes the content and structure of documents including words, phrases, relationships, and values in over 200 languages with tokenization, collation, and stemming for core languages. Functionality includes the ability to toggle range indexes, geospatial indexes, the RDF triple index, and reverse indexes on or off based on your data, the kinds of queries that you will run, and your desired performance. Full-text search MarkLogic supports search across its data and metadata using a word or phrase and incorporates Boolean logic, stemming, wildcards, case sensitivity, punctuation sensitivity, diacritic sensitivity, and search term weighting. Data can be searched using JavaScript, XQuery, SPARQL, and SQL. Semantics MarkLogic uses RDF triples to provide semantics for ease of storing metadata and querying. ACID Unlike other NoSQL databases, MarkLogic maintains ACID consistency for transactions. Replication MarkLogic provides high availability with replica sets. Scalability MarkLogic scales horizontally using sharding. MarkLogic can run over multiple servers, balancing the load or replicating data to keep the system up and running in the event of hardware failure. Security MarkLogic has built in security features such as element-level permissions and data redaction. Optic API for Relational Operations An API that lets developers view their data as documents, graphs or rows. Security MarkLogic provides redaction, encryption, and element-level security (allowing for control on read and write rights on parts of a document). == Applications == Banking Big Data Fraud prevention Insurance Claims Management and Underwriting Master data management Recommendation engines == Licensing == MarkLogic is available under various licensing and delivery models, namely a free Developer or an Essential Enterprise license.[3] Licenses are available from MarkLogic or directly from cloud marketplaces such as Amazon Web Services and Microsoft Azure. == Releases == 2001 – Cerisent XQE 1: ACID transactions, Full-text search, XML Storage, XQuery, Role-based security 2004 – Cerisent XQE 2: Scale-out architecture, Enhanced search (stemming, thesaurus, wildcard), Backup and restore 2005 – MarkLogic Server 3: Continuing search improvements, Content Processing Framework (including PDF, Word, Excel, PPT), Failover 2008 – MarkLogic Server 4: Geospatial search, entity extraction, advanced XQuery, performance, scalability enhancements, auditing 2011 – MarkLogic Server 5: Flexible replication / DDIL, real-time indexing, advanced search, improved analytics, concurrency enhancements 2012 – MarkLogic Server 6: REST and Java APIs, App Builder, enhanced UI, improved search 2013 – MarkLogic Server 7: Semantic graph, bitemporal data, tiered storage, improved search, better management 2015 – MarkLogic Server 8: A Native JSON storage, Server-side JavaScript, Bitemporal, Node.js client API, Incremental backup, Flexible replication[16] 2017 – MarkLogic Server 9: Data integration across Relational and Non-Relational data, Advanced Encryption, Element Level Security, Redaction 2019 – MarkLogic Server 10: Enhanced Data Hub, improved SQL, security, analytics performance, cloud support 2022 – MarkLogic Server 11: MarkLogic Ops Director (Monitoring and Administration Improvements), expanded PKI 2025 – MarkLogic Server 12: Generative AI and Native Vector Search, Graph Algorithm Support, Virtual TDEs (relational views on the fly)
Read more →
Anyword

Anyword is a technology company that offers an artificial intelligence platform, using natural language processing to generate and optimize marketing text for websites, social media, email, and ads. The company also offers a complete managed service to publishers and brands to help them increase their revenue through social ads. It is used by National Geographic, Red Bull, The New York Times, BBC, Ted Baker, etc. The company has an office in New York, and Tel Aviv. == History == It was founded in 2013 — its original name was Keywee Inc. In March 2015, Anyword received $9.1 million in the Series A funding round led by a notable group of investors. In July 2016, the company was selected as an official Facebook Marketing Partner. In August 2019, Anyword was named Best Content Marketing Platform in the Digiday Technology Award winners. In November 2021, it raised $21 million in its Series B funding round.
Read more →
March algorithm

The March algorithm is a widely used algorithm that tests SRAM memory by filling all its entries test patterns. It carries out several passes through an SRAM checking the patterns and writing new patterns. The SRAM read and write operations performed on each pass are called a March element and each element is repeated for each entry. The March algorithm is often used to find functional faults in SRAM during testing such as: Stuck-at Faults (SAFs) Transition Faults (TFs) Address Decoder Faults (AFs) Coupling Faults (CFs), such as Inversion (CFin), Idempotent (CFid), and State (CFst) coupling faults It has been suggested to test SRAM modules using the algorithm before sale using a built-in self-test mechanism. == Notation == Each pass in a test sequence is represented by an "element". An element consists of a vertical arrow to indicate the direction in which the memory is scanned followed by a list of read/write operations to be applied to each memory cell. Multiple elements can be listed, separated by semicolons, to form a "test". For example, { ⇕ ( w 0 ) ; ⇑ ( r 0 , w 1 ) ; ⇓ ( r 1 , w 0 , r 0 ) } {\displaystyle \{\Updownarrow (w0);\Uparrow (r0,w1);\Downarrow (r1,w0,r0)\}} specifies to: Scan in both directions, writing 0. Scan from lowest to highest address, reading 0 and writing 1. Scan from highest to lowest address, reading 1, writing 0 and reading 0. == Variants == Many variants of the March algorithm exist with different sequences of tests. Each variant makes a different tradeoff between what faults it can detect and the complexity of the algorithm. Several variants have been given names:
Read more →
Jeremy Renner Official

Jeremy Renner Official (or Jeremy Renner on the Google Play Store) was a mobile app created by American actor Jeremy Renner. He created the app in March 2017 to hear the input and comments of his fans. The app was shut down in September 2019 in part due to the frequent bullying and trolling that the platform had experienced. The app featured optional microtransactions, with some ranging up to roughly US$400 despite the app itself being free. Upon shutting down the app, Renner issued a mass-refund for the collectible "stars" in the app for purchases made within the last ninety days, from the day the announcement was posted. He then posted an apology to the app itself, and the app was deleted from both the Google Play Store and the App Store shortly after. == Usage == Upon downloading the app, the user was faced with a video of Renner speaking about his fans and superfans, regular giveaways, and real-life updates. While the app was active, Renner posted regular questions and comments for fans. Renner occasionally livestreamed about his work and day-to-day life. The community developed to include memes, selfies, and a "Happy Rennsday" event on Wednesdays. == History == === 2017–2019 === The app launched in March 2017 with a promotional contest. Renner's fans were encouraged to download the app and create comments about being Renner's biggest fan; Renner would then choose a winner and transport the winner and a guest to have lunch with him at the Calgary Expo. In the first few months Renner teased behind-the-scenes of projects he was working on, which he now sporadically does on Instagram. The app was similarly designed to Instagram as well, with a near identically styled layout. Around midway through 2019, a hoax account of Renner was made to mock the celebrity, joking about masturbating to porn and defending another hoax account of Casey Anthony. FastCompany wrote extensively about Renner's app in April 2019, calling it "a surprising new kind of social media". The Ringer stated "Jeremy Renner's Jeremy Renner app is the Jeremy Renner of apps." === After deletion (2019–2020) === After the shutdown of the app, a comedy-based pseudo-app with modular endings was released, called "The Jeremy Renner App Experience", in which the player plays as Jeremy Renner on the day of the Jeremy Renner Official app's shutdown. The app details several different choices on how Renner handles the situation. A six-part podcast was also created to mock the app's deletion, called The Renner Files, featuring Carolyn Goldfarb and Sarah Ramos. == Controversies == === Marketing === One of the main controversies of Renner's app was its marketing. The app's developers, Escapex, specialized in and grew famous for making similar monetized apps for celebrities. The marketing campaign was based on direct contact with Renner, whose chances were increased with regular payments for "stars", although very few encounters seemed to happen with Renner himself. The multiple problems with the app led the CEO of Escapex, Sephi Shapira, to call the app a "freak situation", and added "Am I concerned about this? Not more than I'm concerned about 50 other things I'm dealing with as a startup company." Along with the marketing failures, the app was seen as misrepresenting itself as seemingly erotic with some advertisements featuring Renner suggestively staring at the camera, despite the actual app being initially considered safe for children. === Harassment === After its release in 2017, the app was met with waves of harassment and bullying by many users on the app, most frequently by using impersonation — referenced in Renner's apology/deletion notice. Some death threats were made across the app by fraud accounts pretending to be several controversial celebrities, including O. J. Simpson and Casey Anthony. As early as October 2017, there were claims of censorship, bullying, and "contest-rigging". In September 2019, comedian Stefan Heck publicized his discovery of the fact that replies through the app appeared as if they were sent by Renner himself in push notifications. After several users abused this feature, Renner asked Escapex to shut down the app.
Read more →
Flajolet–Martin algorithm

The Flajolet–Martin algorithm is an algorithm for approximating the number of distinct elements in a stream with a single pass and space-consumption logarithmic in the maximal number of possible distinct elements in the stream (the count-distinct problem). The algorithm was introduced by Philippe Flajolet and G. Nigel Martin in their 1984 article "Probabilistic Counting Algorithms for Data Base Applications". Later it has been refined in "LogLog counting of large cardinalities" by Marianne Durand and Philippe Flajolet, and "HyperLogLog: The analysis of a near-optimal cardinality estimation algorithm" by Philippe Flajolet et al. In their 2010 article "An optimal algorithm for the distinct elements problem", Daniel M. Kane, Jelani Nelson and David P. Woodruff give an improved algorithm, which uses nearly optimal space and has optimal O(1) update and reporting times. == The algorithm == Assume that we are given a hash function h a s h ( x ) {\displaystyle \mathrm {hash} (x)} that maps input x {\displaystyle x} to integers in the range [ 0 ; 2 L − 1 ] {\displaystyle [0;2^{L}-1]} , and where the outputs are sufficiently uniformly distributed. Note that the set of integers from 0 to 2 L − 1 {\displaystyle 2^{L}-1} corresponds to the set of binary strings of length L {\displaystyle L} . For any non-negative integer y {\displaystyle y} , define b i t ( y , k ) {\displaystyle \mathrm {bit} (y,k)} to be the k {\displaystyle k} -th bit in the binary representation of y {\displaystyle y} , such that: y = ∑ k ≥ 0 b i t ( y , k ) 2 k . {\displaystyle y=\sum _{k\geq 0}\mathrm {bit} (y,k)2^{k}.} We then define a function ρ ( y ) {\displaystyle \rho (y)} that outputs the position of the least-significant set bit in the binary representation of y {\displaystyle y} , and L {\displaystyle L} if no such set bit can be found as all bits are zero: ρ ( y ) = { min { k ≥ 0 ∣ b i t ( y , k ) ≠ 0 } y > 0 L y = 0 {\displaystyle \rho (y)={\begin{cases}\min\{k\geq 0\mid \mathrm {bit} (y,k)\neq 0\}&y>0\\L&y=0\end{cases}}} Note that with the above definition we are using 0-indexing for the positions, starting from the least significant bit. For example, ρ ( 13 ) = ρ ( 1101 2 ) = 0 {\displaystyle \rho (13)=\rho (1101_{2})=0} , since the least significant bit is a 1 (0th position), and ρ ( 8 ) = ρ ( 1000 2 ) = 3 {\displaystyle \rho (8)=\rho (1000_{2})=3} , since the least significant set bit is at the 3rd position. At this point, note that under the assumption that the output of our hash function is uniformly distributed, then the probability of observing a hash output ending with 2 k {\displaystyle 2^{k}} (a one, followed by k {\displaystyle k} zeroes) is 2 − ( k + 1 ) {\displaystyle 2^{-(k+1)}} , since this corresponds to flipping k {\displaystyle k} heads and then a tail with a fair coin. Now the Flajolet–Martin algorithm for estimating the cardinality of a multiset M {\displaystyle M} is as follows: Initialize a bit-vector BITMAP to be of length L {\displaystyle L} and contain all 0s. For each element x {\displaystyle x} in M {\displaystyle M} : Calculate the index i = ρ ( h a s h ( x ) ) {\displaystyle i=\rho (\mathrm {hash} (x))} . Set B I T M A P [ i ] = 1 {\displaystyle \mathrm {BITMAP} [i]=1} . Let R {\displaystyle R} denote the smallest index i {\displaystyle i} such that B I T M A P [ i ] = 0 {\displaystyle \mathrm {BITMAP} [i]=0} . Estimate the cardinality of M {\displaystyle M} as 2 R / ϕ {\displaystyle 2^{R}/\phi } , where ϕ ≈ 0.77351 {\displaystyle \phi \approx 0.77351} . The idea is that if n {\displaystyle n} is the number of distinct elements in the multiset M {\displaystyle M} , then B I T M A P [ 0 ] {\displaystyle \mathrm {BITMAP} [0]} is accessed approximately n / 2 {\displaystyle n/2} times, B I T M A P [ 1 ] {\displaystyle \mathrm {BITMAP} [1]} is accessed approximately n / 4 {\displaystyle n/4} times and so on. Consequently, if i ≫ log 2 ⁡ n {\displaystyle i\gg \log _{2}n} , then B I T M A P [ i ] {\displaystyle \mathrm {BITMAP} [i]} is almost certainly 0, and if i ≪ log 2 ⁡ n {\displaystyle i\ll \log _{2}n} , then B I T M A P [ i ] {\displaystyle \mathrm {BITMAP} [i]} is almost certainly 1. If i ≈ log 2 ⁡ n {\displaystyle i\approx \log _{2}n} , then B I T M A P [ i ] {\displaystyle \mathrm {BITMAP} [i]} can be expected to be either 1 or 0. The correction factor ϕ ≈ 0.77351 {\displaystyle \phi \approx 0.77351} (OEIS: A244256) is found by calculations, which can be found in the original article. == Improving accuracy == A problem with the Flajolet–Martin algorithm in the above form is that the results vary significantly. A common solution has been to run the algorithm multiple times with k {\displaystyle k} different hash functions and combine the results from the different runs. One idea is to take the mean of the k {\displaystyle k} results together from each hash function, obtaining a single estimate of the cardinality. The problem with this is that averaging is very susceptible to outliers (which are likely here). A different idea is to use the median, which is less prone to be influences by outliers. The problem with this is that the results can only take form 2 R / ϕ {\displaystyle 2^{R}/\phi } , where R {\displaystyle R} is integer. A common solution is to combine both the mean and the median: Create k ⋅ l {\displaystyle k\cdot l} hash functions and split them into k {\displaystyle k} distinct groups (each of size l {\displaystyle l} ). Within each group use the mean for aggregating together the l {\displaystyle l} results, and finally take the median of the k {\displaystyle k} group estimates as the final estimate. The 2007 HyperLogLog algorithm splits the multiset into subsets and estimates their cardinalities, then it uses the harmonic mean to combine them into an estimate for the original cardinality.
Read more →
Behavior selection algorithm

In artificial intelligence, a behavior selection algorithm, or action selection algorithm, is an algorithm that selects appropriate behaviors or actions for one or more intelligent agents. In game artificial intelligence, it selects behaviors or actions for one or more non-player characters. Common behavior selection algorithms include: Finite-state machines Hierarchical finite-state machines Decision trees Behavior trees Hierarchical task networks Hierarchical control systems Utility systems Dialogue tree (for selecting what to say) == Related concepts == In application programming, run-time selection of the behavior of a specific method is referred to as the strategy design pattern.
Read more →
Document capture software

Document capture software refers to applications that provide the ability and feature set to automate the process of scanning paper documents or importing electronic documents, often for the purposes of feeding advanced document classification and data collection processes. Most scanning hardware, both scanners and copiers, provides the basic ability to scan to any number of image file formats, including: PDF, TIFF, JPG, BMP, etc. This basic functionality is augmented by document capture software, which can add efficiency and standardization to the process. == Typical features == Typical features of Document Capture Software include: Barcode recognition Patch Code recognition Separation Optical Character Recognition (OCR) Optical Mark Recognition (OMR) Quality Assurance Indexing Migration === Goal for implementation of a document capture solution === The goal for implementing a document capture solution is to reduce the amount of time spent scanning, separating, enhancing, organizing, classifying, normalizing, and collecting information from document collections, and to produce metadata along with an image/PDF file, and/or OCR text. This information is then migrated to a file share, FTP site, database, Document Management or Enterprise Content Management system. These systems often provide a search function, allowing search of the assets based on the produced metadata, and then viewed using document imaging software. == General document capture system solutions == === Integration with document management system === ECM (Enterprise Content management) and their DMS component (Document Management System) are being adopted by many organizations as a corporate document management system for all types of electronic files, e.g. MS word, PDF ... However, much of the information held by organisations is on paper and this needs to be integrated within the same document repository. By converting paper documents into digital format through scanning, organizations convert paper into image formats such as TIF, JPG, and PDF, and also extract valuable index information or business data from the document using OCR technology. Digital documents and associated metadata can easily be stored in the ECM in a variety of formats. The most popular of these formats is PDF which not only provides an accurate representation of the document but also allows all the OCR text in the document to be stored behind the PDF image. This format is known as PDF with hidden text or text-searchable PDF. This allows users to search for documents by using keywords in the metadata fields or by searching the content of PDF files across the repository. ==== Advantages of scanning documents into a ECM/DMS ==== Information held on paper is usually just as valuable to organisations as the electronic documents that are generated internally. Often this information represents a large proportion of the day to day correspondence with suppliers and customers. Having the ability to manage and share this information internally through a document management system such as SharePoint or a CMIS-compatible repository improves collaboration between departments or employees and also eliminates the risk of losing this information through disasters such as floods or fire. Organisations adopting an ECM/DMS often implement electronic workflow which allows the information held on paper to be included as part of an electronic business process and incorporated into a customer record file along with other associated office documents and emails. For business critical documents, such as purchase orders and supplier invoices, digitising documents helps speed up business transactions as well as reduce manual effort involved in keying data into business systems, such as CRM, ERP and Accounting. Scanned invoices can also be routed to managers for payment approval via email or an electronic workflow. == Electronic document capture == In the earlier implementations of Document Capture Software, the technology focused solely on the digitization and capture of information from paper documents. Document images were acquired from document scanners via TWAIN/ISIS drivers. Only image-based file formats like TIF, JPG, and BMP were typically compatible with these solutions. But in recent years, as the volume of electronically-created documents and the number of proprietary file formats continues to increase at exponential rates, the need for handling documents existing in electronic formats has grown. The relevant document capture products have adapted to function with non-image file formats with the end-goal of creating a unified processing workflow capable of handling all incoming documents The ability to import files from a variety of sources is one example of such adaptation. Importing documents from ECM/DMS software solutions, email servers, FTP, and EDI is now as much of a requirement of document capture software as is paper capture. The normalization of output files to text-based PDF format is now another critical factor in long-term archival of proprietary electronic file formats. Normalization expands access and usage of files to users throughout the enterprise, rather than only those that created the original electronic file.
Read more →
Sample complexity

The sample complexity of a machine learning algorithm represents the number of training-samples that it needs in order to successfully learn a target function. More precisely, the sample complexity is the number of training-samples that we need to supply to the algorithm, so that the function returned by the algorithm is within an arbitrarily small error of the best possible function, with probability arbitrarily close to 1. There are two variants of sample complexity: The weak variant fixes a particular input-output distribution; The strong variant takes the worst-case sample complexity over all input-output distributions. The No free lunch theorem, discussed below, proves that, in general, the strong sample complexity is infinite, i.e. that there is no algorithm that can learn the globally-optimal target function using a finite number of training samples. However, if we are only interested in a particular class of target functions (e.g., only linear functions) then the sample complexity is finite, and it depends linearly on the VC dimension on the class of target functions. == Definition == Let X {\displaystyle X} be a space which we call the input space, and Y {\displaystyle Y} be a space which we call the output space, and let Z {\displaystyle Z} denote the product X × Y {\displaystyle X\times Y} . For example, in the setting of binary classification, X {\displaystyle X} is typically a finite-dimensional vector space and Y {\displaystyle Y} is the set { − 1 , 1 } {\displaystyle \{-1,1\}} . Fix a hypothesis space H {\displaystyle {\mathcal {H}}} of functions h : X → Y {\displaystyle h\colon X\to Y} . A learning algorithm over H {\displaystyle {\mathcal {H}}} is a computable map from Z {\displaystyle Z} to H {\displaystyle {\mathcal {H}}} . In other words, it is an algorithm that takes as input a finite sequence of training samples and outputs a function from X {\displaystyle X} to Y {\displaystyle Y} . Typical learning algorithms include empirical risk minimization, without or with Tikhonov regularization. Fix a loss function L : Y × Y → R ≥ 0 {\displaystyle {\mathcal {L}}\colon Y\times Y\to \mathbb {R} _{\geq 0}} , for example, the square loss L ( y , y ′ ) = ( y − y ′ ) 2 {\displaystyle {\mathcal {L}}(y,y')=(y-y')^{2}} , where h ( x ) = y ′ {\displaystyle h(x)=y'} . For a given distribution ρ {\displaystyle \rho } on X × Y {\displaystyle X\times Y} , the expected risk of a hypothesis (a function) h ∈ H {\displaystyle h\in {\mathcal {H}}} is E ( h ) := E ρ [ L ( h ( x ) , y ) ] = ∫ X × Y L ( h ( x ) , y ) d ρ ( x , y ) {\displaystyle {\mathcal {E}}(h):=\mathbb {E} _{\rho }[{\mathcal {L}}(h(x),y)]=\int _{X\times Y}{\mathcal {L}}(h(x),y)\,d\rho (x,y)} In our setting, we have h = A ( S n ) {\displaystyle h={\mathcal {A}}(S_{n})} , where A {\displaystyle {\mathcal {A}}} is a learning algorithm and S n = ( ( x 1 , y 1 ) , … , ( x n , y n ) ) ∼ ρ n {\displaystyle S_{n}=((x_{1},y_{1}),\ldots ,(x_{n},y_{n}))\sim \rho ^{n}} is a sequence of vectors which are all drawn independently from ρ {\displaystyle \rho } . Define the optimal risk E H ∗ = inf h ∈ H E ( h ) . {\displaystyle {\mathcal {E}}_{\mathcal {H}}^{}={\underset {h\in {\mathcal {H}}}{\inf }}{\mathcal {E}}(h).} Set h n = A ( S n ) {\displaystyle h_{n}={\mathcal {A}}(S_{n})} , for each sample size n {\displaystyle n} . h n {\displaystyle h_{n}} is a random variable and depends on the random variable S n {\displaystyle S_{n}} , which is drawn from the distribution ρ n {\displaystyle \rho ^{n}} . The algorithm A {\displaystyle {\mathcal {A}}} is called consistent if E ( h n ) {\displaystyle {\mathcal {E}}(h_{n})} probabilistically converges to E H ∗ {\displaystyle {\mathcal {E}}_{\mathcal {H}}^{}} . In other words, for all ϵ , δ > 0 {\displaystyle \epsilon ,\delta >0} , there exists a positive integer N {\displaystyle N} , such that, for all sample sizes n ≥ N {\displaystyle n\geq N} , we have Pr ρ n [ E ( h n ) − E H ∗ ≥ ε ] < δ . {\displaystyle \Pr _{\rho ^{n}}[{\mathcal {E}}(h_{n})-{\mathcal {E}}_{\mathcal {H}}^{}\geq \varepsilon ]<\delta .} The sample complexity of A {\displaystyle {\mathcal {A}}} is then the minimum N {\displaystyle N} for which this holds, as a function of ρ , ϵ {\displaystyle \rho ,\epsilon } , and δ {\displaystyle \delta } . We write the sample complexity as N ( ρ , ϵ , δ ) {\displaystyle N(\rho ,\epsilon ,\delta )} to emphasize that this value of N {\displaystyle N} depends on ρ , ϵ {\displaystyle \rho ,\epsilon } , and δ {\displaystyle \delta } . If A {\displaystyle {\mathcal {A}}} is not consistent, then we set N ( ρ , ϵ , δ ) = ∞ {\displaystyle N(\rho ,\epsilon ,\delta )=\infty } . If there exists an algorithm for which N ( ρ , ϵ , δ ) {\displaystyle N(\rho ,\epsilon ,\delta )} is finite, then we say that the hypothesis space H {\displaystyle {\mathcal {H}}} is learnable. In others words, the sample complexity N ( ρ , ϵ , δ ) {\displaystyle N(\rho ,\epsilon ,\delta )} defines the rate of consistency of the algorithm: given a desired accuracy ϵ {\displaystyle \epsilon } and confidence δ {\displaystyle \delta } , one needs to sample N ( ρ , ϵ , δ ) {\displaystyle N(\rho ,\epsilon ,\delta )} data points to guarantee that the risk of the output function is within ϵ {\displaystyle \epsilon } of the best possible, with probability at least 1 − δ {\displaystyle 1-\delta } . In probably approximately correct (PAC) learning, one is concerned with whether the sample complexity is polynomial, that is, whether N ( ρ , ϵ , δ ) {\displaystyle N(\rho ,\epsilon ,\delta )} is bounded by a polynomial in 1 / ϵ {\displaystyle 1/\epsilon } and 1 / δ {\displaystyle 1/\delta } . If N ( ρ , ϵ , δ ) {\displaystyle N(\rho ,\epsilon ,\delta )} is polynomial for some learning algorithm, then one says that the hypothesis space H {\displaystyle {\mathcal {H}}} is PAC-learnable. This is a stronger notion than being learnable. == Unrestricted hypothesis space: infinite sample complexity == One can ask whether there exists a learning algorithm so that the sample complexity is finite in the strong sense, that is, there is a bound on the number of samples needed so that the algorithm can learn any distribution over the input-output space with a specified target error. More formally, one asks whether there exists a learning algorithm A {\displaystyle {\mathcal {A}}} , such that, for all ϵ , δ > 0 {\displaystyle \epsilon ,\delta >0} , there exists a positive integer N {\displaystyle N} such that for all n ≥ N {\displaystyle n\geq N} , we have sup ρ ( Pr ρ n [ E ( h n ) − E H ∗ ≥ ε ] ) < δ , {\displaystyle \sup _{\rho }\left(\Pr _{\rho ^{n}}[{\mathcal {E}}(h_{n})-{\mathcal {E}}_{\mathcal {H}}^{}\geq \varepsilon ]\right)<\delta ,} where h n = A ( S n ) {\displaystyle h_{n}={\mathcal {A}}(S_{n})} , with S n = ( ( x 1 , y 1 ) , … , ( x n , y n ) ) ∼ ρ n {\displaystyle S_{n}=((x_{1},y_{1}),\ldots ,(x_{n},y_{n}))\sim \rho ^{n}} as above. The No Free Lunch Theorem says that without restrictions on the hypothesis space H {\displaystyle {\mathcal {H}}} , this is not the case, i.e., there always exist "bad" distributions for which the sample complexity is arbitrarily large. Thus, in order to make statements about the rate of convergence of the quantity sup ρ ( Pr ρ n [ E ( h n ) − E H ∗ ≥ ε ] ) , {\displaystyle \sup _{\rho }\left(\Pr _{\rho ^{n}}[{\mathcal {E}}(h_{n})-{\mathcal {E}}_{\mathcal {H}}^{}\geq \varepsilon ]\right),} one must either constrain the space of probability distributions ρ {\displaystyle \rho } , e.g. via a parametric approach, or constrain the space of hypotheses H {\displaystyle {\mathcal {H}}} , as in distribution-free approaches. == Restricted hypothesis space: finite sample-complexity == The latter approach leads to concepts such as VC dimension and Rademacher complexity which control the complexity of the space H {\displaystyle {\mathcal {H}}} . A smaller hypothesis space introduces more bias into the inference process, meaning that E H ∗ {\displaystyle {\mathcal {E}}_{\mathcal {H}}^{}} may be greater than the best possible risk in a larger space. However, by restricting the complexity of the hypothesis space it becomes possible for an algorithm to produce more uniformly consistent functions. This trade-off leads to the concept of regularization. It is a theorem from VC theory that the following three statements are equivalent for a hypothesis space H {\displaystyle {\mathcal {H}}} : H {\displaystyle {\mathcal {H}}} is PAC-learnable. The VC dimension of H {\displaystyle {\mathcal {H}}} is finite. H {\displaystyle {\mathcal {H}}} is a uniform Glivenko-Cantelli class. This gives a way to prove that certain hypothesis spaces are PAC learnable, and by extension, learnable. === An example of a PAC-learnable hypothesis space === X = R d , Y = { − 1 , 1 } {\displaystyle X=\mathbb {R} ^{d},Y=\{-1,1\}} , and let H {\displaystyle {\mathcal {H}}} be the space of affine functions on X {\displaystyle X} , that is, functions of the form x ↦ ⟨ w , x ⟩ + b {\displaystyle x\mapsto \langl
Read more →
Reverse data management

Reverse data management describes a branch and set of research questions in relational database theory that aim to reverse the common focus of standard data management. Instead of focusing on the "forward" transformation of an input databases (a set of relational tables) to an output table, which is the main focus of standard query evaluation, reverse data management reverses that focus and studies the possible input database transformations that would achieve a desired output. Usually the objective is to find an intervention (a deletion, addition, or change of tuples) of minimal size, in order to achieve a particular change in the output. The problem has been studied at least since the 1980s, but has received renewed attention due to an influential paper in the early 2000s that made a connection between provenance and view propagation. The term was coined in a VLDB 2011 vision paper. The problem has been receiving significant attention in recent years due to its connection to computational fairness. == Topics in reverse data management problems == Example topics in reverse data management include: Deletion propagation with source side-effects: Find a minimal number of tuples to delete in the database in order to delete a particular tuple in the output. Deletion propagation with view side-effects: Find a set of tuples to delete in the database in order to delete a particular tuple in the output, while removing the minimal number of other output tuples. Causal responsibility: Find a minimal number of tuples to delete in the database in order to make a particular input tuple counterfactual. This notion is inspired by the notions of actual cause and causal responsibility from the work of Halpern and Pearl. Resilience: Find a minimal number of tuples to delete in the database in order to make a Boolean query false. The complexity of this problem is identical to the problem of deletion propagation with source-side effects over a different database. Smallest witness problem: Find a minimal number of tuples to keep in the a database (or equivalently, delete a maximal number of tuples) while keeping a particular tuple in the output. Minimum repair: Given a database that violates certain integrity constraints, find a minimal number of tuples to delete in the database in order to fulfill all constraints (also called to "repair" the database).
Read more →
Ontology alignment

Ontology alignment, or ontology matching, is the process of determining correspondences between concepts in ontologies. A set of correspondences is also called an alignment. The phrase takes on a slightly different meaning, in computer science, cognitive science or philosophy. == Computer science == For computer scientists, concepts are expressed as labels for data. Historically, the need for ontology alignment arose out of the need to integrate heterogeneous databases, ones developed independently and thus each having their own data vocabulary. In the Semantic Web context involving many actors providing their own ontologies, ontology matching has taken a critical place for helping heterogeneous resources to interoperate. Ontology alignment tools find classes of data that are semantically equivalent, for example, "truck" and "lorry". The classes are not necessarily logically identical. According to Euzenat and Shvaiko (2007), there are three major dimensions for similarity: syntactic, external, and semantic. Coincidentally, they roughly correspond to the dimensions identified by Cognitive Scientists below. A number of tools and frameworks have been developed for aligning ontologies, some with inspiration from Cognitive Science and some independently. Ontology alignment tools have generally been developed to operate on database schemas, XML schemas, taxonomies, formal languages, entity-relationship models, dictionaries, and other label frameworks. They are usually converted to a graph representation before being matched. Since the emergence of the Semantic Web, such graphs can be represented in the Resource Description Framework line of languages by triples of the form , as illustrated in the Notation 3 syntax. In this context, aligning ontologies is sometimes referred to as "ontology matching". The problem of Ontology Alignment has been tackled recently by trying to compute matching first and mapping (based on the matching) in an automatic fashion. Systems like DSSim, X-SOM or COMA++ obtained at the moment very high precision and recall. The Ontology Alignment Evaluation Initiative aims to evaluate, compare and improve the different approaches. === Formal definition === Given two ontologies i = ⟨ C i , R i , I i , T i , V i ⟩ {\displaystyle i=\langle C_{i},R_{i},I_{i},T_{i},V_{i}\rangle } and j = ⟨ C j , R j , I j , T j , V j ⟩ {\displaystyle j=\langle C_{j},R_{j},I_{j},T_{j},V_{j}\rangle } where C {\displaystyle C} is the set of classes, R {\displaystyle R} is the set of relations, I {\displaystyle I} is the set of individuals, T {\displaystyle T} is the set of data types, and V {\displaystyle V} is the set of values, we can define different types of (inter-ontology) relationships. Such relationships will be called, all together, alignments and can be categorized among different dimensions: similarity vs logic: this is the difference between matchings (predicating about the similarity of ontology terms), and mappings (logical axioms, typically expressing logical equivalence or inclusion among ontology terms) atomic vs complex: whether the alignments we considered are one-to-one, or can involve more terms in a query-like formulation (e.g., LAV/GAV mapping) homogeneous vs heterogeneous: do the alignments predicate on terms of the same type (e.g., classes are related only to classes, individuals to individuals, etc.) or we allow heterogeneity in the relationship? type of alignment: the semantics associated to an alignment. It can be subsumption, equivalence, disjointness, part-of or any user-specified relationship. Subsumption, atomic, homogeneous alignments are the building blocks to obtain richer alignments, and have a well defined semantics in every Description Logic. Let's now introduce more formally ontology matching and mapping. An atomic homogeneous matching is an alignment that carries a similarity degree s ∈ [ 0 , 1 ] {\displaystyle s\in [0,1]} , describing the similarity of two terms of the input ontologies i {\displaystyle i} and j {\displaystyle j} . Matching can be either computed, by means of heuristic algorithms, or inferred from other matchings. Formally we can say that, a matching is a quadruple m = ⟨ i d , t i , t j , s ⟩ {\displaystyle m=\langle id,t_{i},t_{j},s\rangle } , where t i {\displaystyle t_{i}} and t j {\displaystyle t_{j}} are homogeneous ontology terms, s {\displaystyle s} is the similarity degree of m {\displaystyle m} . A (subsumption, homogeneous, atomic) mapping is defined as a pair μ = ⟨ t i , t j ⟩ {\displaystyle \mu =\langle t_{i},t_{j}\rangle } , where t i {\displaystyle t_{i}} and t j {\displaystyle t_{j}} are homogeneous ontology terms. == Cognitive science == For cognitive scientists interested in ontology alignment, the "concepts" are nodes in a semantic network that reside in brains as "conceptual systems." The focal question is: if everyone has unique experiences and thus different semantic networks, then how can we ever understand each other? This question has been addressed by a model called ABSURDIST (Aligning Between Systems Using Relations Derived Inside Systems for Translation). Three major dimensions have been identified for similarity as equations for "internal similarity, external similarity, and mutual inhibition." == Ontology alignment methods == Two sub research fields have emerged in ontology mapping, namely monolingual ontology mapping and cross-lingual ontology mapping. The former refers to the mapping of ontologies in the same natural language, whereas the latter refers to "the process of establishing relationships among ontological resources from two or more independent ontologies where each ontology is labelled in a different natural language". Existing matching methods in monolingual ontology mapping are discussed in Euzenat and Shvaiko (2007). Approaches to cross-lingual ontology mapping are presented in Fu et al. (2011).
Read more →
Affective computing

Affective computing is the study and development of systems and devices that can recognize, interpret, process, and simulate human affects. It is an interdisciplinary field spanning computer science, psychology, and cognitive science. While some core ideas in the field may be traced as far back as to early philosophical inquiries into emotion, the modern idea originated with Rosalind Picard's 1995 paper entitled "Affective Computing" and her 1997 book of the same name published by MIT Press. One motivation for researching affective computing is the ability to give machines emotional intelligence, including simulating empathy. The goal is that a machine should interpret the emotional state of humans and adapt its behavior to those emotions, responding appropriately. Recent experimental research has shown that subtle affective haptic feedback can shape human reward learning and mobile interaction behavior, suggesting that affective computing systems may not only interpret emotional states but also actively modulate user actions through emotion-laden outputs. == Areas == === Detecting and recognizing emotional information === Detecting emotional information usually begins with passive sensors that capture data about the user's physical state or behavior without interpreting the input. The data gathered is analogous to the cues humans use to perceive emotions in others. For example, a video camera might capture facial expressions, body posture, and gestures, while a microphone might capture speech. Other sensors detect emotional cues by directly measuring physiological data, such as skin temperature and galvanic resistance. Recognizing emotional information requires the extraction of meaningful patterns from the gathered data. This is done using machine learning techniques that process different modalities, such as speech recognition, natural language processing, or facial expression detection. The goal of most of these techniques is to produce labels that would match the labels a human would give in the same situation. For example, if a person makes a facial expression furrowing their brow, then the computer vision system might be trained to label their face as appearing "confused" or as "concentrating" or "slightly negative" (as opposed to positive, which it might say if they were smiling in a happy-appearing way). This response is based on the data used to train the system. These labels may or may not correspond to what the person is actually feeling. === Emotion in machines === Another area within affective computing is the design of computational devices proposed to exhibit either innate emotional capabilities or that are capable of convincingly simulating emotions. A more practical approach, based on current technological capabilities, is the simulation of emotions in conversational agents in order to enrich and facilitate interactivity between human and machine. Marvin Minsky, one of the pioneering computer scientists in artificial intelligence, relates emotions to the broader issues of machine intelligence stating in The Emotion Machine that emotion is "not especially different from the processes that we call 'thinking.'" The innovative approach "digital humans" or virtual humans includes an attempt to give these programs, which simulate humans, an emotional dimension as well, including reactions, facial expressions, and gestures in accordance with the reaction that a real person would have in certain emotionally stimulating situations. Emotion in machines often refers to emotion in computational, often AI-based, systems. As a result, the terms 'emotional AI' is being used. Some modern large language models simulate emotions in their chats with humans. ChatGPT's simulated emotion leans more positive than that of most human responses. == Technologies == In psychology, cognitive science, and in neuroscience, there have been two main approaches for describing how humans perceive and classify emotion: continuous or categorical. The continuous approach tends to use dimensions such as negative vs. positive, calm vs. aroused. The categorical approach tends to use discrete classes such as happy, sad, angry, fearful, surprise, and disgust. Different kinds of machine learning regression and classification models are used for machines to produce continuous or discrete labels. Sometimes, models are also built that allow combinations across the categories (e.g. a happy-surprised face or a fearful-surprised face). The following sections consider many of the kinds of input data used for the task of emotion recognition. === Emotional speech === Various changes in the autonomic nervous system can indirectly alter a person's speech, and affective technologies can leverage this information to recognize emotion. For example, speech produced in a state of fear, anger, or joy becomes fast, loud, and precisely enunciated, with a higher and wider range in pitch, whereas emotions such as tiredness, boredom, or sadness tend to generate slow, low-pitched, and slurred speech. Some emotions have been found to be more easily computationally identified, such as anger or approval. Emotional speech processing technologies recognize the user's emotional state using computational analysis of speech features. Vocal parameters and prosodic features such as pitch variables and speech rate can be analyzed through pattern recognition techniques. Speech analysis is an effective method of identifying affective state, having an average reported accuracy of 70-80% in research from 2003 and 2006. These systems tend to outperform average human accuracy (approximately 60%) but are less accurate than systems which employ other modalities for emotion detection, such as physiological states or facial expressions. However, since many speech characteristics are independent of semantics or culture, this technique is considered to be a promising route for further research. ==== Algorithms ==== The process of speech/text affect detection requires the creation of a reliable database, knowledge base, or vector space model, broad enough to fit every need for its application, as well as the selection of a successful classifier which will allow for quick and accurate emotion identification. As of 2010, the most frequently used classifiers were linear discriminant classifiers (LDC), k-nearest neighbor (k-NN), Gaussian mixture model (GMM), support vector machines (SVM), artificial neural networks (ANN), decision tree algorithms, and hidden Markov models (HMMs). Various studies showed that choosing the appropriate classifier can significantly enhance the overall performance of the system. The list below gives a brief description of each algorithm: LDC – Classification happens based on the value obtained from the linear combination of the feature values, which are usually provided in the form of vector features. k-NN – Classification happens by locating the object in the feature space, and comparing it with the k nearest neighbors (training examples). The majority vote decides on the classification. GMM – A probabilistic model used for representing the existence of subpopulations within the overall population. Each sub-population is described using the mixture distribution, which allows for classification of observations into the sub-populations. SVM – A type of (usually binary) linear classifier which decides in which of the two (or more) possible classes, each input may fall into. ANN – is a mathematical model, inspired by biological neural networks, that can better grasp possible non-linearities of the feature space. Decision tree algorithms – work based on following a decision tree in which leaves represent the classification outcome, and branches represent the conjunction of subsequent features that lead to the classification. HMMs – a statistical Markov model in which the states and state transitions are not directly available to observation. Instead, the series of outputs dependent on the states are visible. In the case of affect recognition, the outputs represent the sequence of speech feature vectors, which allow the deduction of states' sequences through which the model progressed. The states can consist of various intermediate steps in the expression of an emotion, and each of them has a probability distribution over the possible output vectors. The states' sequences allow us to predict the affective state which we are trying to classify, and this is one of the most commonly used techniques within the area of speech affect detection. It has been proven that having enough acoustic evidence available the emotional state of a person can be classified by a set of majority voting classifiers. The proposed set of classifiers is based on three main classifiers: kNN, C4.5 and SVM-RBF Kernel. This set achieves better performance than each basic classifier taken separately. It is compared with two other sets of classifiers: one-against-all (OAA) multiclass SVM with Hybrid kernels and th
Read more →
WaveNet

WaveNet is a deep neural network for generating raw audio. It was created by researchers at London-based AI firm DeepMind. The technique, outlined in a paper in September 2016, is able to generate relatively realistic-sounding human-like voices by directly modelling waveforms using a neural network method trained with recordings of real speech. Tests with US English and Mandarin reportedly showed that the system outperforms Google's best existing text-to-speech (TTS) systems, although as of 2016 its text-to-speech synthesis still was less convincing than actual human speech. WaveNet's ability to generate raw waveforms means that it can model any kind of audio, including music. == History == Generating speech from text is an increasingly common task thanks to the popularity of software such as Apple's Siri, Microsoft's Cortana, Amazon Alexa and the Google Assistant. Most such systems use a variation of a technique that involves concatenated sound fragments together to form recognisable sounds and words. The most common of these is called concatenative TTS. It consists of large library of speech fragments, recorded from a single speaker that are then concatenated to produce complete words and sounds. The result sounds unnatural, with an odd cadence and tone. The reliance on a recorded library also makes it difficult to modify or change the voice. Another technique, known as parametric TTS, uses mathematical models to recreate sounds that are then assembled into words and sentences. The information required to generate the sounds is stored in the parameters of the model. The characteristics of the output speech are controlled via the inputs to the model, while the speech is typically created using a voice synthesiser known as a vocoder. This can also result in unnatural sounding audio. == Design and ongoing research == === Background === WaveNet is a type of feedforward neural network known as a deep convolutional neural network (CNN). In WaveNet, the CNN takes a raw signal as an input and synthesises an output one sample at a time. It does so by sampling from a softmax (i.e. categorical) distribution of a signal value that is encoded using μ-law companding transformation and quantized to 256 possible values. === Initial concept and results === According to the original September 2016 DeepMind research paper WaveNet: A Generative Model for Raw Audio, the network was fed real waveforms of speech in English and Mandarin. As these pass through the network, it learns a set of rules to describe how the audio waveform evolves over time. The trained network can then be used to create new speech-like waveforms at 16,000 samples per second. These waveforms include realistic breaths and lip smacks – but do not conform to any language. WaveNet is able to accurately model different voices, with the accent and tone of the input correlating with the output. For example, if it is trained with German, it produces German speech. The capability also means that if the WaveNet is fed other inputs – such as music – its output will be musical. At the time of its release, DeepMind showed that WaveNet could produce waveforms that sound like classical music. === Content (voice) swapping === According to the June 2018 paper Disentangled Sequential Autoencoder, DeepMind has successfully used WaveNet for audio and voice "content swapping": the network can swap the voice on an audio recording for another, pre-existing voice while maintaining the text and other features from the original recording. "We also experiment on audio sequence data. Our disentangled representation allows us to convert speaker identities into each other while conditioning on the content of the speech." (p. 5) "For audio, this allows us to convert a male speaker into a female speaker and vice versa [...]." (p. 1) According to the paper, a two-digit minimum amount of hours (c. 50 hours) of pre-existing speech recordings of both source and target voice are required to be fed into WaveNet for the program to learn their individual features before it is able to perform the conversion from one voice to another at a satisfying quality. The authors stress that "[a]n advantage of the model is that it separates dynamical from static features [...]." (p. 8), i. e. WaveNet is capable of distinguishing between the spoken text and modes of delivery (modulation, speed, pitch, mood, etc.) to maintain during the conversion from one voice to another on the one hand, and the basic features of both source and target voices that it is required to swap on the other. The January 2019 follow-up paper Unsupervised speech representation learning using WaveNet autoencoders details a method to successfully enhance the proper automatic recognition and discrimination between dynamical and static features for "content swapping", notably including swapping voices on existing audio recordings, in order to make it more reliable. Another follow-up paper, Sample Efficient Adaptive Text-to-Speech, dated September 2018 (latest revision January 2019), states that DeepMind has successfully reduced the minimum amount of real-life recordings required to sample an existing voice via WaveNet to "merely a few minutes of audio data" while maintaining high-quality results. Its ability to clone voices has raised ethical concerns about WaveNet's ability to mimic the voices of living and dead persons. According to a 2016 BBC article, companies working on similar voice-cloning technologies (such as Adobe Voco) intend to insert watermarking inaudible to humans to prevent counterfeiting, while maintaining that voice cloning satisfying, for instance, the needs of entertainment-industry purposes would be of a far lower complexity and use different methods than required to fool forensic evidencing methods and electronic ID devices, so that natural voices and voices cloned for entertainment-industry purposes could still be easily told apart by technological analysis. == Applications == At the time of its release, DeepMind said that WaveNet required too much computational processing power to be used in real world applications. As of October 2017, Google announced a 1,000-fold performance improvement along with better voice quality. WaveNet was then used to generate Google Assistant voices for US English and Japanese across all Google platforms. In November 2017, DeepMind researchers released a research paper detailing a proposed method of "generating high-fidelity speech samples at more than 20 times faster than real-time", called "Probability Density Distillation". At the annual I/O developer conference in May 2018, it was announced that new Google Assistant voices were available and made possible by WaveNet; WaveNet greatly reduced the number of audio recordings that were required to create a voice model by modeling the raw audio of the voice actor samples.
Read more →
Single-source publishing

Single-source publishing, also known as single-sourcing publishing, is a content management method which allows the same source content to be used across different forms of media and more than one time. The labor-intensive and expensive work of editing need only be carried out once, on only one document; that source document (the single source of truth) can then be stored in one place and reused. This reduces the potential for error, as corrections are only made one time in the source document. The benefits of single-source publishing primarily relate to the editor rather than the user. The user benefits from the consistency that single-sourcing brings to terminology and information. This assumes the content manager has applied an organized conceptualization to the underlying content (A poor conceptualization can make single-source publishing less useful). Single-source publishing is sometimes used synonymously with multi-channel publishing though whether or not the two terms are synonymous is a matter of discussion. == Definition == While there is a general definition of single-source publishing, there is no single official delineation between single-source publishing and multi-channel publishing, nor are there any official governing bodies to provide such a delineation. Single-source publishing is most often understood as the creation of one source document in an authoring tool and converting that document into different file formats or human languages (or both) multiple times with minimal effort. Multi-channel publishing can either be seen as synonymous with single-source publishing, or similar in that there is one source document but the process itself results in more than a mere reproduction of that source. == History == The origins of single-source publishing lie, indirectly, with the release of Windows 3.0 in 1990. With the eclipsing of MS-DOS by graphical user interfaces, help files went from being unreadable text along the bottom of the screen to hypertext systems such as WinHelp. On-screen help interfaces allowed software companies to cease the printing of large, expensive help manuals with their products, reducing costs for both producer and consumer. This system raised opportunities as well, and many developers fundamentally changed the way they thought about publishing. Writers of software documentation did not simply move from being writers of traditional bound books to writers of electronic publishing, but rather they became authors of central documents which could be reused multiple times across multiple formats. The first single-source publishing project was started in 1993 by Cornelia Hofmann at Schneider Electric in Seligenstadt, using software based on Interleaf to automatically create paper documentation in multiple languages based on a single original source file. XML, developed during the mid- to late-1990s, was also significant to the development of single-source publishing as a method. XML, a markup language, allows developers to separate their documentation into two layers: a shell-like layer based on presentation and a core-like layer based on the actual written content. This method allows developers to write the content only one time while switching it in and out of multiple different formats and delivery methods. In the mid-1990s, several firms began creating and using single-source content for technical documentation (Boeing Helicopter, Sikorsky Aviation and Pratt & Whitney Canada) and user manuals (Ford owners manuals) based on tagged SGML and XML content generated using the Arbortext Epic editor with add-on functions developed by a contractor. The concept behind this usage was that complex, hierarchical content that did not lend itself to discrete componentization could be used across a variety of requirements by tagging the differences within a single document using the capabilities built into SGML and XML. Ford, for example, was able to tag its single owner's manual files so that 12 model years could be generated via a resolution script running on the single completed file. Pratt & Whitney, likewise, was able to tag up to 20 subsets of its jet engine manuals in single-source files, calling out the desired version at publication time. World Book Encyclopedia also used the concept to tag its articles for American and British versions of English. Starting from the early 2000s, single-source publishing was used with an increasing frequency in the field of technical translation. It is still regarded as the most efficient method of publishing the same material in different languages. Once a printed manual was translated, for example, the online help for the software program which the manual accompanies could be automatically generated using the method. Metadata could be created for an entire manual and individual pages or files could then be translated from that metadata with only one step, removing the need to recreate information or even database structures. Although single-source publishing is now decades old, its importance has increased urgently as of the 2010s. As consumption of information products rises and the number of target audiences expands, so does the work of developers and content creators. Within the industry of software and its documentation, there is a perception that the choice is to embrace single-source publishing or render one's operations obsolete. == Criticism == Editors using single-source publishing have been criticized for below-standard work quality, leading some critics to describe single-source publishing as the "conveyor belt assembly" of content creation. While heavily used in technical translation, there are risks of error in regard to indexing. While two words might be synonyms in English, they may not be synonyms in another language. In a document produced via single-sourcing, the index will be translated automatically and the two words will be rendered as synonyms. This is because they are synonyms in the source language, while in the target language they are not.
Read more →
March algorithm

The March algorithm is a widely used algorithm that tests SRAM memory by filling all its entries test patterns. It carries out several passes through an SRAM checking the patterns and writing new patterns. The SRAM read and write operations performed on each pass are called a March element and each element is repeated for each entry. The March algorithm is often used to find functional faults in SRAM during testing such as: Stuck-at Faults (SAFs) Transition Faults (TFs) Address Decoder Faults (AFs) Coupling Faults (CFs), such as Inversion (CFin), Idempotent (CFid), and State (CFst) coupling faults It has been suggested to test SRAM modules using the algorithm before sale using a built-in self-test mechanism. == Notation == Each pass in a test sequence is represented by an "element". An element consists of a vertical arrow to indicate the direction in which the memory is scanned followed by a list of read/write operations to be applied to each memory cell. Multiple elements can be listed, separated by semicolons, to form a "test". For example, { ⇕ ( w 0 ) ; ⇑ ( r 0 , w 1 ) ; ⇓ ( r 1 , w 0 , r 0 ) } {\displaystyle \{\Updownarrow (w0);\Uparrow (r0,w1);\Downarrow (r1,w0,r0)\}} specifies to: Scan in both directions, writing 0. Scan from lowest to highest address, reading 0 and writing 1. Scan from highest to lowest address, reading 1, writing 0 and reading 0. == Variants == Many variants of the March algorithm exist with different sequences of tests. Each variant makes a different tradeoff between what faults it can detect and the complexity of the algorithm. Several variants have been given names:
Read more →