Tales from the Loop (Swedish: Ur Varselklotet), subtitled "Roleplaying in the '80s That Never Was", is an alternative history science fiction tabletop role-playing game published in 2017 by Free League Publishing, the international arm of Swedish game and book publisher Fria Ligan AB, and Modiphius Entertainment. The game, based on the art of Simon Stålenhag, envisions an alternative world where a group of bored and ignored preteens and teens solve mysteries caused by new technology near their hometown. == Description == === Setting === Tales from the Loop is set in an alternative history world taken from the artwork of Simon Stålenhag. According to this alternative timeline, back in the 1940s, research began on particle accelerators. In the 1960s, two massive underground particle accelerators were built in Sweden and Colorado with the promise of a harvest of technological marvels that would change everyone's lives. Tales from the Loop is set twenty years later, in the late 1980s, and the better life has not materialized. Although the particle accelerators have created robots and large skyships, the detritus of failed experiments and the ruins of abandoned high tech company buildings litter the landscape. Generally the life of the average family has not changed for the better. A campaign can either be set in the Mälaren Islands, west of the Swedish capital of Stockholm, or in a city in the Southwest United States that resembles Boulder City, Nevada. There is also a step-by-step guide for the gamemaster to use their own hometown. === Character generation === Player characters are preteens and young teenagers age 10–15 who live in a society where they are bored and largely left to themselves. Players can choose archetypes for their characters including Bookworm, Jock, Troublemaker, Popular Kid and Weirdo. Unlike most role-playing games, characters in Tales from the Loop cannot be killed, although in an ongoing campaign or due to an in-game effect, they are removed from the game if they reach the age of sixteen. === Game system === The game uses the Year Zero Engine first developed by Tomas Härenstam for the post-apocalyptic role-playing game Mutant: Year Zero. (Härenstam served as the editor and project manager for Tales from the Loop.) Problems are resolved by rolling a pool of six-sided dice, with any 6 rolled marking success. Attributes and skills (Sneak, Force, Move, Build, Tinker, Calculate, Contact, Charm, Lead, Investigate, Comprehend, and Empathize) may allow the player to add more dice to the dice pool, increasing the chances of success. However, if a character has earned a condition such as Scared or Injured, dice are removed from the dice pool. === Gameplay === The game principles are that life for the characters is dull and boring, but the area around the town is full of wonderful, mysterious things. An adventure is set up as a Mystery, and in order to successfully resolve the Mystery, characters must overcome a series of Troubles, which can range from having to be home by a certain time to dealing with a bully to disarming or otherwise overcoming a booby-trap on a door that must be opened. Each Mystery is played as a series of scenes, much like a TV drama. Although the gamemaster leads the players into the Mystery, each scene is set collaboratively with the players before action continues. As critic Jukka Kauppinen noted, "The players and the gamemaster take turns verbally staging a new scene — where we are, what it's like there — and only then what we do." === Campaign === The book presents a chronologically-linked set of four Mysteries called "The Four Seasons of Mad Science" that take place over a calendar year: "Summer Break and Killer Birds": The Kids hears pigeons having a conversation and investigate "Grown-Up Attraction": Adults start disappearing without any sign of struggle. "Creatures from the Cretaceous": The search for a missing dog leads to the discovery of creatures that don't belong in our time "I, Wagner": The Kids discover a body in a stream, and are drawn into a Mystery with robots and humans that may affect them closely. == Publication history == In 2017, Swedish artist Simon Stålenhag was raising money on Kickstarter to publish a book of his art titled Tales from the Loop. One of the stretch goals offered was the creation of a role-playing game. A second Kickstarter campaign to publish the role-playing game was initiated by Fria Ligan AB, who surpassed their crowdfunding goal and raised a total of 3,745,896 kr from 5,600 backers. The role-playing game Tales from the Loop was subsequently published as a 184-page hardcover book in 2017 by Free League Publishing, the international arm of Swedish game and book publisher Fria Ligan AB, and Modiphius Entertainment. Cover art and interior art were by Stålenhag, and cartography was by Christian Granath. A stand-alone expansion, Things from the Flood (Swedish: Flodskörden), based on Stålenhag's art book of the same name, was created by Nils Hintze, Rickard Antroia, and Tomas Härenstam. The 216-page hardcover book was published in 2019 with cover art by Stålenhag, interior art by Stålenhag and Reine Rosenberg, and cartography by Christian Granath. In 2020, the setting of the role-playing game was transferred to the TV series Tales from the Loop developed by Nathanial Halpern and Simon Stålenhag. The series tells eight stories of children's encounters with strange technology. == Reception == Shut Up & Sit Down praised Tales from the Loop for its comfortable, contemporary setting, simple rules that make the game easy to run, and the alternation between sci-fi and the kids' lives, but criticized the Type system for characters, noting "a suggested 'Pride' for the Weirdo involved being homosexual –– the only mention of queerness in the entire game. Those of us who identify as GLBTQ bristled at that: why was only the Weirdo queer, with queerness as a (possibly secret) Pride? Why not more fully address being a GLBTQ kid in the 1980s?" The review concluded, "For new RPG players, Tales is a decent game that you'll enjoy and that will make your heart burst. But you need an experienced GM who’s able to either alter the book’s mysteries or create their own, and who can put in work when poor dice rolls hold the players back." Rob Weiland of Geek & Sundry named Tales from the Loop 2017's best RPG release and praised Stålenhag's art, the collaborative nature between the GM and players, and the simplicity of running the game. Weiland concluded, "It has a simple system that is easy to explain but holds up under several plays. It has a setting that’s immediately evocative but also leaves plenty of room for GMs to build out their own world. It offers players a chance to experience the rush of memory, the pain of childhood and the wonder of movies." In a review of Tales from the Loop in Black Gate, Andrew Zimmerman Jones said, "Though not based directly on an established franchise, it draws richly from elements of popular culture that will make it resonate with many players. The focus on narrative play also means it’s a good game for people who aren’t necessarily big into learning a ton of new rules." Jukka Kauppinen, writing for the Finnish games magazine Skrolli, called the game, "downright delicious in its diversity. The science fiction world created by the Swedish artist Simon Stälenhag is, after all, both delightful vintage and tickling novelty." Kauppinen concluded, "This mutual storytelling and interaction makes this game more of a campfire circle than a traditional role-playing game. At the same time, its setting in the real world, tinged with science fiction and even horror, creates a delicious and unique adventure environment." In his 2023 book Monsters, Aliens, and Holes in the Ground, RPG historian Stu Horvath noted that the game system "pushes the players to constantly reevaluate their characters' relationships with the everyday world, for better or worse. It won't be long before navigating entanglements with parents, teachers, siblings and bullies proves just as risky to the characters, and central to the players' experience, as trying to find out what happened with the time portal or dealing with a rampaging robot." Horvath concluded, "The appeal of Tales from the Loop is Stålenhag's deep shadows and purple dusks. They hide the dangers and mysteries that often act [as] an escape hatch, a way to avoid prosaic problems." == Awards == At the 2017 Golden Geek Awards, Tales of the Loop won "RPG of the Year", and was a finalist for " Best RPG Artwork/Presentation" At the 2017 ENnie Awards, Tales from the Loops won five Gold Medals: Product of the Year Best Writing Best Setting Best Game Best Art, Interior
Private cloud computing infrastructure
Private cloud computing infrastructure is a category of cloud computing that provides comparable benefits to public cloud systems, such as self-service and scalability, but it does so via a proprietary framework. In contrast to public clouds, which cater to multiple entities, a private cloud is specifically designed for the requirements and objectives of one organization. == Definition == A private cloud computing infrastructure constitutes a distinctive model of cloud computing that facilitates a secure and distinct cloud environment where only the intended client can function. It can either be physically housed in the organization's in-house data center or be managed by a third-party provider. In a private cloud, the infrastructure and services are always sustained on a private network, and both the hardware and software are devoted exclusively to a single organization. == History == The concept of private cloud infrastructure started to take shape around the mid-2000s, coinciding with the rise of other cloud computing forms. It came into existence as a solution to the shortcomings of public clouds, particularly concerns over data control, security, and network performance. IT departments began to mirror the automation and self-service features of the public cloud in their data centers. Over time, these services became more advanced, and private cloud technology has been refined to address businesses and organizations' diverse needs. == Architecture == Private cloud computing infrastructure generally involves a mix of hardware, network infrastructure, and virtualization software. The hardware, often referred to as a cloud server or cloud array, consists of a server rack or a collection of server racks containing the storage and processors that constitute the cloud. The virtualization software, such as Hyper-V, OpenStack, or VMWare, establishes and oversees virtual machines with which users interact. The network infrastructure connects the private cloud to users and may facilitate connectivity with other on-premises data centers or clouds. == Applications == Private cloud infrastructures are usually utilized by medium to large businesses and organizations that need robust control over their data, have extensive computing needs, or have specific regulatory or compliance obligations. This includes healthcare organizations, government agencies, financial institutions, and any business that needs to process and store large data volumes.
Nicholas Carlini
Nicholas Carlini is an American researcher affiliated with Anthropic and previously with Google DeepMind who has published research in the fields of computer security and machine learning. He is known for his work on adversarial machine learning, particularly his work on the Carlini & Wagner attack in 2016. This attack was particularly useful in defeating defensive distillation, a method used to increase model robustness, and has since been effective against other defenses against adversarial input. In 2018, Carlini demonstrated an attack on Mozilla's DeepSpeech model, showing that hidden commands could be embedded in speech inputs, which the model would execute even if they were inaudible to humans. He also led a team at UC Berkeley that successfully broke seven out of nine defenses against adversarial attacks presented at the 2018 International Conference on Learning Representations. In addition to his work on adversarial attacks, Carlini has made significant contributions to understanding the privacy risks of machine learning models. In 2020, he revealed that large language models, like GPT-2, could memorize and output personally identifiable information. His research demonstrated that this issue worsened with larger models, and he later showed similar vulnerabilities in generative image models, such as Stable Diffusion. == Life and career == Nicholas Carlini obtained his Bachelor of Arts in Computer Science and Mathematics from the University of California, Berkeley, in 2013. He then continued his studies at the same university, where he pursued a PhD under the supervision of David Wagner, completing it in 2018. Carlini became known for his work on adversarial machine learning. In 2016, he worked alongside Wagner to develop the Carlini & Wagner attack, a method of generating adversarial examples against machine learning models. The attack was proved to be useful against defensive distillation, a popular mechanism where a student model is trained based on the features of a parent model to increase the robustness and generalizability of student models. The attack gained popularity when it was shown that the methodology was also effective against most other defenses, rendering them ineffective. In 2018, Carlini demonstrated an attack against Mozilla Foundation's DeepSpeech model where he showed that by hiding malicious commands inside normal speech input the speech model would respond to the hidden commands even when the commands were not discernible by humans. In the same year, Carlini and his team at UC Berkeley showed that out of the 11 papers presenting defenses to adversarial attacks accepted in that year's ICLR conference, seven of the defenses could be broken. Since 2021, he and his team have been working on large language models, creating a questionnaire where humans typically scored 35% whereas AI models scored in the 40%, with GPT-3 getting 38% which could be improved to 40% through few shot prompting. The best performer in the test was UnifiedQA, a model developed by Google specifically for answer questions and answer sets. Carlini has also developed methods to cause large language models like ChatGPT to answer harmful questions like how to construct bombs. He is also known for his work studying the privacy of machine learning models. In 2020, he showed for the first time that large language models would memorize some of the text data that they were trained on. For example, he found that GPT-2 could output personally identifiable information. He then led an analysis of larger models and studied how memorization increased with model size. Then, in 2022 he showed the same vulnerability in generative image models, and specifically diffusion models, by showing that Stable Diffusion could output images of people's faces that it was trained on. Following on this, Carlini then showed that ChatGPT would also sometimes output exact copies of webpages it was trained on, including personally identifiable information. Some of these studies have since been referenced by the courts in debating the copyright status of AI models. == Other work == Carlini received the Best of Show award at the 2020 IOCCC for implementing a tic-tac-toe game entirely with calls to printf, expanding on work from a research paper of his from 2015. The judges commented on his submission "This year's Best of Show (carlini) is such a novel way of obfuscation that it would be worth of a special mention in the (future) Best of IOCCC list!". [sic] == Awards == Best Student Paper Award, IEEE S&P 2017 ("Towards Evaluating the Robustness of Neural Networks") Best Paper Award, ICML 2018 ("Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples") Distinguished Paper Award, USENIX 2021 ("Poisoning the Unlabeled Dataset of Semi-Supervised Learning") Distinguished Paper Award, USENIX 2023 ("Tight Auditing of Differentially Private Machine Learning") Best Paper Award, ICML 2024 ("Stealing Part of a Production Language Model") Best Paper Award, ICML 2024 ("Considerations for Differentially Private Learning with Large-Scale Public Pretraining")
Stephen Wolfram
Stephen Wolfram ( WUUL-frəm; born 29 August 1959) is a British-American computer scientist, physicist, and businessman. He is known for his work in computer algebra and theoretical physics. In 2012, he was named a fellow of the American Mathematical Society. As a businessman, Wolfram is the founder and CEO of the software company Wolfram Research, where he works as chief designer of Mathematica and the Wolfram Alpha answer engine. == Early life == === Family === Stephen Wolfram was born in London in 1959 to Hugo and Sybil Wolfram, both German Jewish refugees to the United Kingdom. His maternal grandmother was British psychoanalyst Kate Friedlander. Wolfram's father, Hugo Wolfram, was a textile manufacturer and served as managing director of the Lurex Company—makers of the fabric Lurex. Wolfram's mother, Sybil Wolfram, was a Fellow and Tutor in Philosophy at Lady Margaret Hall at University of Oxford from 1964 to 1993. Wolfram is married to a mathematician. They have four children together. === Education === Wolfram was educated at Eton College, but left prematurely in 1976. As a young child, Wolfram had difficulties learning arithmetic. He entered St. John's College, Oxford, at age 17 and left in 1978 without graduating to attend the California Institute of Technology the following year, where he received a PhD in particle physics in 1980. Wolfram's thesis committee was composed of Richard Feynman, Peter Goldreich, Frank J. Sciulli, and Steven Frautschi, and chaired by Richard D. Field. == Early career == Wolfram, at the age of 15, began research in applied quantum field theory and particle physics and published scientific papers in peer-reviewed scientific journals; by the time he left Oxford, he had published ten such papers. Following his PhD, Wolfram joined the faculty at Caltech and became the youngest recipient of a MacArthur Fellowship in 1981, at age 21. == Later career == === Complex systems and cellular automata === In 1983, Wolfram left for the School of Natural Sciences of the Institute for Advanced Study in Princeton. By that time, he was no longer interested in particle physics. Instead, he began pursuing investigations into cellular automata, mainly with computer simulations. He produced a series of papers investigating the class of elementary cellular automata, conceiving the Wolfram code, a naming system for one-dimensional cellular automata, and a classification scheme for the complexity of their behaviour. He conjectured that the Rule 110 cellular automaton might be Turing complete, which a research assistant to Wolfram, Matthew Cook, later proved correct. Wolfram sued Cook and temporarily blocked publication of the work on Rule 110 for allegedly violating a non-disclosure agreement until Wolfram could publish the work in his controversial book A New Kind of Science. Wolfram's cellular-automata work came to be cited in more than 10,000 papers. In the mid-1980s, Wolfram worked on simulations of physical processes (such as turbulent fluid flow) with cellular automata on the Connection Machine alongside Richard Feynman and helped initiate the field of complex systems. In 1984, he was a participant in the Founding Workshops of the Santa Fe Institute, along with Nobel laureates Murray Gell-Mann, Manfred Eigen, and Philip Warren Anderson, and future laureate Frank Wilczek. In 1986, he founded the Center for Complex Systems Research (CCSR) at the University of Illinois Urbana–Champaign. In 1987, he founded the journal Complex Systems. === Symbolic Manipulation Program === Wolfram led the development of the computer algebra system SMP (Symbolic Manipulation Program) in the Caltech physics department during 1979–1981. A dispute with the administration over the intellectual property rights regarding SMP—patents, copyright, and faculty involvement in commercial ventures—eventually led him to resign from Caltech. SMP was further developed and marketed commercially by Inference Corp. of Los Angeles during 1983–1988. === Mathematica === In 1986, Wolfram left the Institute for Advanced Study for the University of Illinois Urbana–Champaign, where he had founded their Center for Complex Systems Research, and started to develop the computer algebra system Mathematica, which was released on 23 June 1988, when he left academia. In 1987, he founded Wolfram Research, which continues to develop and market the program. === A New Kind of Science === From 1992 to 2002, Wolfram worked on his controversial book A New Kind of Science, which presents an empirical study of simple computational systems. Additionally, it argues that for fundamental reasons these types of systems, rather than traditional mathematics, are needed to model and understand complexity in nature. Wolfram's conclusion is that the universe is discrete in its nature, and runs on fundamental laws that can be described as simple programs. He predicts that a realization of this within scientific communities will have a revolutionary influence on physics, chemistry, biology, and most other scientific areas, hence the book's title. The book was met with skepticism and criticism that Wolfram took credit for the work of others and made conclusions without evidence to support them. === Wolfram Alpha computational knowledge engine === In March 2009, Wolfram announced Wolfram Alpha, an answer engine. Wolfram Alpha launched in May 2009, and a paid-for version with extra features launched in February 2012 that was met with criticism for its high price, which later dropped from $50 to $2. The engine is based on natural language processing and a large library of rules-based algorithms. The application programming interface allows other applications to extend and enhance Wolfram Alpha. === Touchpress === In 2010, Wolfram co-founded Touchpress with Theodore Gray, Max Whitby, and John Cromie. The company specialised in creating in-depth premium apps and games covering a wide range of educational subjects designed for children, parents, students, and educators. Touchpress published more than 100 apps. The company is no longer active. === Wolfram Language === In March 2014, at the annual South by Southwest (SXSW) event, Wolfram officially announced the Wolfram Language as a new general multi-paradigm programming language, though it was previously available through Mathematica and not an entirely new programming language. The documentation for the language was pre-released in October 2013 to coincide with the bundling of Mathematica and the Wolfram Language on every Raspberry Pi computer with some controversy because of the proprietary nature of the Wolfram Language. While the Wolfram Language has existed for over 30 years as the primary programming language used in Mathematica, it was not officially named until 2014, and is not widely used. === Wolfram Physics Project === In April 2020, Wolfram announced the "Wolfram Physics Project" as an effort to reduce and explain all the laws of physics within a paradigm of a hypergraph that is transformed by minimal rewriting rules that obey the Church–Rosser property. The effort is a continuation of the ideas he originally described in A New Kind of Science. Wolfram claims that "From an extremely simple model, we're able to reproduce special relativity, general relativity and the core results of quantum mechanics." Physicists are generally unimpressed with Wolfram's claim, and say his results are non-quantitative and arbitrary. == Personal interests and activities == Wolfram has a log of personal analytics, including emails received and sent, keystrokes made, meetings and events attended, recordings of phone calls, and even physical movement dating back to the 1980s. In the preface of A New Kind of Science, he noted that he recorded over 100 million keystrokes and 100 mouse miles. He has said that personal analytics "can give us a whole new dimension to experiencing our lives." Wolfram was a scientific consultant for the 2016 film Arrival. He and his son Christopher Wolfram wrote some of the code featured on screen, such as the code in graphics depicting an analysis of the alien logograms, for which they used the Wolfram Language.
Julia Hirschberg
Julia Hirschberg is an American computer scientist noted for her research on computational linguistics and natural language processing. She received her first PhD in history from the University of Michigan and the second from the University of Pennsylvania in computer science doing research in Natural Language Processing. She worked at Bell Labs and AT&T Bell Labs from 1985 to 2002 and from 2002 at Columbia University where she is currently the Percy K. and Vida L. W. Hudson Professor of Computer Science. == Biography == Julia Linn Bell Hirschberg received her first Ph.D. degree in history (16th-century Mexico) from University of Michigan in 1976. She served on the History faculty of Smith College from 1974 to 1982. She subsequently shifted to Computer Science studies, receiving her M.S. in Computer and Information Science from University of Pennsylvania in 1982 and a Ph.D. in Computer and Information Science from University of Pennsylvania in 1985. Upon graduation from University of Pennsylvania in 1985, Hirschberg joined AT&T Bell Labs as a Member of Technical staff in the Linguistics Research Department, where she worked on improving prosody assignment for Text-to-Speech Synthesis (TTS) in the Bell Labs TTS system. She was promoted to Department Head in 1994 when she created a new Human Computer Interface Research Lab. She and her department remained at Bell Labs until 1996 when they moved to AT&T Labs Research as part of a corporate reorganization. In 2002, she joined the Columbia University faculty as a professor in the Department of Computer Science. She served as Chair of the Computer Science Department from 2012 to 2018. She still leads classes at Columbia in speech and natural language research and supervises PhD students and a large number of research project students. == Research == Hirschberg's research has included prosody, discourse structure, conversational implicature, text-to-speech synthesis, speech summarization, spoken dialogue systems, emotional speech, deceptive speech, charismatic speech, entrainment, empathetic speech and code-switching. Hirschberg was among the first to combine Natural Language Processing (NLP) approaches to discourse and dialogue with speech research. She pioneered techniques in text analysis for prosody assignment in Text-to-Speech synthesis at Bell laboratories in the 1980s and 1990s, developing corpus-based statistical models based upon syntactic and discourse information which are in general use today in TTS systems. With Janet Pierrehumbert, she developed a theoretical model of intonational meaning. She was a leader in the development of the ToBI conventions for intonational description, which have been extended to numerous languages and which today are the most widely used standard for intonational annotation. Hirschberg has been a pioneer together with Gregory Ward in much experimental work on intonational sources of language meaning and how these interact with pragmatic phenomena, particularly on the meaning of accent (intonational prominent) items and the meaning of intonational contours. She also has innovated in numerous other areas involving prosody and meaning, including the role of grammatical function and surface position in pitch accent location, the use of prosody in disambiguating cue phrases (discourse markers) with Diane Litman, the role of prosody in disambiguation in English, Italian, and Spanish with Cinzia Avesani and Pilar Prieto, and the automatic identification of speech recognition errors using prosodic information, At AT&T Labs she worked with Fernando Pereira, Steve Whittaker, and others on speech search and developing new interfaces for speech navigation. At Columbia, she and her students have continued and extended research on spoken dialogue systems (automatically detecting speech recognition errors and inappropriate system queries, modeling turn-taking behavior, dialogue entrainment, modeling and generating clarification dialogues); on the automatic classification of trust, charisma, deception and emotion from speech; on speech summarization; prosody translation, hedging behavior in text and speech, text-to-speech synthesis, and speech search in low resource languages. She also holds several patents in TTS and in speech search. Corpora she and collaborators have collected include the Boston Directions Corpus, the Columbia SRI Colorado Deception Corpus, and the Columbia Games Corpus. She has served on numerous technical boards and editorial committees. She has served as a member of the Computing Research Association's (CRA) Board of Directors and as co-chair of CRA-W. She is also noted for her leadership in broadening participation in computing. == Awards == Hirschberg's notable honors and awards include: Elected as a member of the National Academy of Artificial Intelligence Academy of Sciences and recipient of the NAAI Artificial Intelligence Exploration Award, 2025 Elected as a Fellow of Asia-Pacific Artificial Intelligence Association (AAIA), 2024. 2020 ISCA Special Service Medal Honorary Doctorate (eredoctoraat) from Tilburg University, Netherlands, 2018. American Academy of Arts and Sciences, 2018. IEEE Fellow, 2017 National Academy of Engineering, 2017 ACM Fellow in 2015 Elected member, American Philosophical Society, 2014. Honorary member, Association for Laboratory Phonology, 2014. Association for Computational Linguistics (ACL) (Founding) Fellow, 2011. International Speech Communication Association (ISCA) Medal for Scientific Achievement, 2011. IEEE James L. Flanagan Speech and Audio Processing Award, 2011. Honorary Doctorate (Hedersdoktorer), KTH (Royal Institute of Technology) Stockholm, Sweden, 2007. AAAI Fellow, 1994. == Publications == A social history of Puebla de Los Ángeles, 1531-60, 1976 Empirical studies on the disambiguation of cue phrases, 1991 Prosody and conversation, 1998 Most recent publications and other information, https://www.cs.columbia.edu/speech/.
Learning to rank
Learning to rank (LTR) or machine-learned ranking (MLR) is the application of machine learning, often supervised, semi-supervised or reinforcement learning, in the construction of ranking models for information retrieval and recommender systems. Training data may, for example, consist of lists of items with some partial order specified between items in each list. This order is typically induced by giving a numerical or ordinal score or a binary judgment (e.g. "relevant" or "not relevant") for each item. The goal of constructing the ranking model is to rank new, unseen lists in a similar way to rankings in the training data. == Applications == === In information retrieval === Ranking is a central part of many information retrieval problems, such as document retrieval, collaborative filtering, sentiment analysis, and online advertising. A possible architecture of a machine-learned search engine is shown in the accompanying figure. Training data consists of queries and documents matching them together with the relevance degree of each match. It may be prepared manually by human assessors (or raters, as Google calls them), who check results for some queries and determine relevance of each result. It is not feasible to check the relevance of all documents, and so typically a technique called pooling is used — only the top few documents, retrieved by some existing ranking models are checked. This technique may introduce selection bias. Alternatively, training data may be derived automatically by analyzing clickthrough logs (i.e. search results which got clicks from users), query chains, or such search engines' features as Google's (since-replaced) SearchWiki. Clickthrough logs can be biased by the tendency of users to click on the top search results on the assumption that they are already well-ranked. Training data is used by a learning algorithm to produce a ranking model which computes the relevance of documents for actual queries. Typically, users expect a search query to complete in a short time (such as a few hundred milliseconds for web search), which makes it impossible to evaluate a complex ranking model on each document in the corpus, and so a two-phase scheme is used. First, a small number of potentially relevant documents are identified using simpler retrieval models which permit fast query evaluation, such as the vector space model, Boolean model, weighted AND, or BM25. This phase is called top- k {\displaystyle k} document retrieval and many heuristics were proposed in the literature to accelerate it, such as using a document's static quality score and tiered indexes. In the second phase, a more accurate but computationally expensive machine-learned model is used to re-rank these documents. === In other areas === Learning to rank algorithms have been applied in areas other than information retrieval: In machine translation for ranking a set of hypothesized translations; In computational biology for ranking candidate 3-D structures in protein structure prediction problems; In recommender systems for identifying a ranked list of related news articles to recommend to a user after he or she has read a current news article. == Feature vectors == For the convenience of MLR algorithms, query-document pairs are usually represented by numerical vectors, which are called feature vectors. Such an approach is sometimes called bag of features and is analogous to the bag of words model and vector space model used in information retrieval for representation of documents. Components of such vectors are called features, factors or ranking signals. They may be divided into three groups (features from document retrieval are shown as examples): Query-independent or static features — those features, which depend only on the document, but not on the query. For example, PageRank or document's length. Such features can be precomputed in off-line mode during indexing. They may be used to compute document's static quality score (or static rank), which is often used to speed up search query evaluation. Query-dependent or dynamic features — those features, which depend both on the contents of the document and the query, such as TF-IDF score or other non-machine-learned ranking functions. Query-level features or query features, which depend only on the query. For example, the number of words in a query. Some examples of features, which were used in the well-known LETOR dataset: TF, TF-IDF, BM25, and language modeling scores of document's zones (title, body, anchors text, URL) for a given query; Lengths and IDF sums of document's zones; Document's PageRank, HITS ranks and their variants. Selecting and designing good features is an important area in machine learning, which is called feature engineering. == Evaluation measures == There are several measures (metrics) which are commonly used to judge how well an algorithm is doing on training data and to compare the performance of different MLR algorithms. Often a learning-to-rank problem is reformulated as an optimization problem with respect to one of these metrics. Examples of ranking quality measures: Mean average precision (MAP); DCG and NDCG; Precision@n, NDCG@n, where "@n" denotes that the metrics are evaluated only on top n documents; Mean reciprocal rank; Kendall's tau; Spearman's rho. DCG and its normalized variant NDCG are usually preferred in academic research when multiple levels of relevance are used. Other metrics such as MAP, MRR and precision, are defined only for binary judgments. Recently, there have been proposed several new evaluation metrics which claim to model user's satisfaction with search results better than the DCG metric: Expected reciprocal rank (ERR); Yandex's pfound. Both of these metrics are based on the assumption that the user is more likely to stop looking at search results after examining a more relevant document, than after a less relevant document. == Approaches == Learning to Rank approaches are often categorized using one of three approaches: pointwise (where individual documents are ranked), pairwise (where pairs of documents are ranked into a relative order), and listwise (where an entire list of documents are ordered). Tie-Yan Liu of Microsoft Research Asia has analyzed existing algorithms for learning to rank problems in his book Learning to Rank for Information Retrieval. He categorized them into three groups by their input spaces, output spaces, hypothesis spaces (the core function of the model) and loss functions: the pointwise, pairwise, and listwise approach. In practice, listwise approaches often outperform pairwise approaches and pointwise approaches. This statement was further supported by a large scale experiment on the performance of different learning-to-rank methods on a large collection of benchmark data sets. In this section, without further notice, x {\displaystyle x} denotes an object to be evaluated, for example, a document or an image, f ( x ) {\displaystyle f(x)} denotes a single-value hypothesis, h ( ⋅ ) {\displaystyle h(\cdot )} denotes a bi-variate or multi-variate function and L ( ⋅ ) {\displaystyle L(\cdot )} denotes the loss function. === Pointwise approach === In this case, it is assumed that each query-document pair in the training data has a numerical or ordinal score. Then the learning-to-rank problem can be approximated by a regression problem — given a single query-document pair, predict its score. Formally speaking, the pointwise approach aims at learning a function f ( x ) {\displaystyle f(x)} predicting the real-value or ordinal score of a document x {\displaystyle x} using the loss function L ( f ; x j , y j ) {\displaystyle L(f;x_{j},y_{j})} . A number of existing supervised machine learning algorithms can be readily used for this purpose. Ordinal regression and classification algorithms can also be used in pointwise approach when they are used to predict the score of a single query-document pair, and it takes a small, finite number of values. === Pairwise approach === In this case, the learning-to-rank problem is approximated by a classification problem — learning a binary classifier h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} that can tell which document is better in a given pair of documents. The classifier shall take two documents as its input and the goal is to minimize a loss function L ( h ; x u , x v , y u , v ) {\displaystyle L(h;x_{u},x_{v},y_{u,v})} . The loss function typically reflects the number and magnitude of inversions in the induced ranking. In many cases, the binary classifier h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} is implemented with a scoring function f ( x ) {\displaystyle f(x)} . As an example, RankNet adapts a probability model and defines h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} as the estimated probability of the document x u {\displaystyle x_{u}} has higher quality than x v {\displaystyle x_{v}} : P u , v ( f ) = CDF ( f ( x u ) − f ( x v ) ) , {\displaystyle P_{u,v}(f)={\text{CDF}
Barney Pell
Barney Pell (born March 18, 1968) is an American entrepreneur, angel investor and computer scientist. He was co-founder and CEO of Powerset, a pioneering natural language search startup, search strategist and architect for Microsoft's Bing search engine, a pioneer in the field of general game playing in artificial intelligence, and the architect of the first intelligent agent to fly onboard and control a spacecraft. He was co-founder, Vice Chairman and Chief Strategy Officer of Moon Express; co-founder and chairman of LocoMobi; and Associate Founder of Singularity University. == Career == === Education === Pell received his Bachelor of Science degree in symbolic systems from Stanford University in 1989, where he graduated Phi Beta Kappa and was a National Merit Scholar. Pell earned a PhD in computer science from Cambridge University in 1993, supervised by Stephen Pulman, where he was a Marshall Scholar. === Research === Pell's research is focused on basic problems in the study of intelligence, computer game playing, machine learning, natural language processing, autonomous robotics, and web search. Barney Pell has published over 30 technical papers on topics related to information retrieval, knowledge management, machine learning, artificial intelligence, and scheduling systems. In computer game playing and machine learning, he was a pioneer in the field of General Game Playing, and created programs to generate the rules of chess-like games and programs to play individual games directly from the rules without human assistance. He also did early work on machine learning in the game of Go and on an architecture for pragmatic reasoning for bidding in the game of Bridge. In natural language processing, he was a scientist in the Artificial Intelligence Center at SRI International, where he worked on the Core Language Engine. Barney Pell was the Technical Area Manager of the Collaborative and Assistant Systems area within the Computational Sciences Division (now the Intelligent Systems Division) at NASA Ames Research Center, where he oversaw a staff of 80 scientists working on information retrieval, search, knowledge management, machine learning, semantic technology, human centered systems, collaboration technology, adaptive user interfaces, human robot interaction, and other areas of artificial intelligence. From 1993 to 1998, Barney Pell worked as a Principal Investigator and Senior Computer Scientist at NASA Ames, where he conducted advanced research and development of autonomous control software for NASA's deep space missions. He was the Architect for the Deep Space One Remote Agent Experiment and the Project Lead for the Executive component of the Remote Agent Experiment, the first intelligent agent to fly onboard and control a spacecraft. === Business === Pell is an entrepreneur who has founded or co-founded several business ventures, including Powerset, Moon Express, and LocoMobi. He was the founder and CEO of Powerset, a San Francisco startup company that built a search engine based on natural language processing technology originally developed at XEROX PARC. On May 11, 2008, the company unveiled a tool for searching a fixed subset of Wikipedia using conversational phrases rather than keywords. On July 1, 2008, Microsoft signed an agreement to acquire Powerset for an estimated $100 million. Powerset became a part of Microsoft's search engine, Bing. From 2008 until August 2011, Pell served as Partner, Search Strategist, and Evangelist for Microsoft's search engine, Bing and as Head of Bing's Local and Mobile Search teams. Prior to joining Powerset, Pell was an Entrepreneur-in-Residence at Mayfield Fund, a venture capital firm in Silicon Valley. Pell is also a founder of Moon Express, Inc., a U.S. company awarded a $10M commercial lunar contract by NASA and a competitor in the Google Lunar X PRIZE. Pell was also co-founder and chairman of LocoMobi, Inc., a U.S. company developing mobile, software and hardware technology solutions for the parking industry. LocoMobi was winner of the Tie50 Award in 2014. Pell is also an associate founder of Singularity University and a Machine Learning Fellow at the Creative Destruction Lab at the Rotman School of Management From 1998 to 2000, Pell served as chief strategist and vice president of business development at StockMaster.com (acquired by Red Herring in March, 2000). From 2000 to 2002, Pell was Chief Strategist and Vice President of Business Development for Whizbang Labs. Pell has been an angel investor and advisor to numerous startup companies, including Pulse.io (acquired by Google), Aardvark (acquired by Google), Appjet (acquired by Google), Jibe Mobile (acquired by Google), Movity (acquired by Trulia), QuestBridge, BrandYourself, CrowdFlower (acquired by Appen), and LinkedIn. === Views and predictions === Pell has expressed views and predictions regarding technological advancements in coming years. He believes that humans will soon have "brain-machine interfaces that will let people interact with each other as if they had 'hangouts' in their mind." Pell predicts these interfaces to become available within 20 to 30 years. Pell also predicts advancements in bodily augmentation, such as "even-better-than-human prosthetics and high-quality tissue engineering within 10 years." Pell believes that with advancements in space exploration technology the moon will soon be a commercially viable resource for material such as platinum and water. == Awards and recognition == In 1986, Pell was awarded a National Merit Scholarship. In 1989, Pell was awarded a Marshall Scholarship. In 1989, Pell was elected Phi Beta Kappa. In 1997, Pell was part of the team award a NASA Software of the Year Award for the Deep Space 1 Remote Agent.