Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

Deep Learning

THE DESIGN AND ANALYSIS OF EXPERIMENTS. By Oscar Kempthorne. New York, John Wiley and Sons, Inc., 1952. 631 pp. $8.50. This book by a teacher of statistics (as well as a consultant for \"experimenters\") is a comprehensive study of the philosophical background for the statistical design of experiment. It is necessary to have some facility with algebraic notation and manipulation to be able to use the volume intelligently. The problems are presented from the theoretical point of view, without such practical examples as would be helpful for those not acquainted with mathematics. The mathematical justification for the techniques is given. As a somewhat advanced treatment of the design and analysis of experiments, this volume will be interesting and helpful for many who approach statistics theoretically as well as practically. With emphasis on the \"why,\" and with description given broadly, the author relates the subject matter to the general theory of statistics and to the general problem of experimental inference. MARGARET J. ROBERTSON

The Design and Analysis of Experiments

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Data Mining - Concepts and Techniques.

Statistical approaches to processing natural language text have become dominant in recent years This foundational text is the first comprehensive introduction to statistical natural language processing (NLP) to appear The book contains all the theory and algorithms needed for building NLP tools It provides broad but rigorous coverage of mathematical and linguistic foundations, as well as detailed discussion of statistical methods, allowing students and researchers to construct their own implementations The book covers collocation finding, word sense disambiguation, probabilistic parsing, information retrieval, and other applications

/pdf/foundations-of-statistical-natural-language-processing-1ou5e6c2q6.pdf

Foundations of Statistical Natural Language Processing

It must certainly be accounted a paradox that probabilistic modeling is simultaneously one of the oldest and one of the newest areas in psycholinguistics. Much research in linguistics and psycholinguistics in the 1950s was statistical and probabilistic. But this research disappeared throughout the 60’s, 70’s, and 80’s. In a highly unscientific survey (conducted by myself) of six college textbooks and handbooks in psycholinguistics published in the last 10 years, not a single one of them mentions the word ‘probability’ in the index. This omission is astonishing when we consider that the input to language comprehension is noisy, ambiguous, and unsegmented. In order to deal with these problems, computational models of speech processing, by contrast, have had to rely on probabilistic models for over 30 years. Computational techniques for processing of text, an input medium which is much less noisy than speech, rely just as heavily on probability theory. Just to pick an arbitrary indicator, 77% of the papers in the year 2000 annual conference of the Association for Computational Linguistics relied on probabilistic models of language processing or learning. Probability theory is certainly the best normative model for solving problems of decisionmaking under uncertainty. But perhaps it is a good normative model, but a bad descriptive one. Despite the fact that probability theory was originally invented as a cognitive model of human reasoning under uncertainty, perhaps people do not use probabilistic reasoning in cognitive tasks like language production and comprehension. Perhaps human language processing is simply a non-optimal, non-rational process? In the last decade or so, there is an emerging consensus that human cognition is in fact rational, and relies on probabilistic processing. The seminal work of Anderson (1990) gave Bayesian underpinnings to cognitive models of memory, categorization, and causation. Probabilistic models have cropped up in many areas of cognition; one area in which there are a number of recent probabilistic models is categorization (Rehder 1999; Glymour and Cheng 1998; Tenenbaum 2000; Tenenbaum and Griffiths 2001b; Tenenbaum and Griffiths 2001a), Probabilistic models are also now finally being applied in psycholinguistics, drawing from early Bayesian-esque precursers in perception such as the Luce (1959) choice rule and the work of Massaro. What does it mean to claim that human language processing is probabilistic? This claim has implications for language comprehension, production and learning.

/pdf/probabilistic-modeling-in-psycholinguistics-linguistic-4ywtwl8v2n.pdf

Probabilistic Modeling in Psycholinguistics: Linguistic Comprehension and Production

The majority of online reviews consist of plain-text feedback together with a single numeric score. However, there are multiple dimensions to products and opinions, and understanding the `aspects' that contribute to users' ratings may help us to better understand their individual preferences. For example, a user's impression of an audiobook presumably depends on aspects such as the story and the narrator, and knowing their opinions on these aspects may help us to recommend better products. In this paper, we build models for rating systems in which such dimensions are explicit, in the sense that users leave separate ratings for each aspect of a product. By introducing new corpora consisting of five million reviews, rated with between three and six aspects, we evaluate our models on three prediction tasks: First, we use our model to uncover which parts of a review discuss which of the rated aspects. Second, we use our model to summarize reviews, which for us means finding the sentences that best explain a user's rating. Finally, since aspect ratings are optional in many of the datasets we consider, we use our model to recover those ratings that are missing from a user's evaluation. Our model matches state-of-the-art approaches on existing small-scale datasets, while scaling to the real-world datasets we introduce. Moreover, our model is able to `disentangle' content and sentiment words: we automatically learn content words that are indicative of a particular aspect as well as the aspect-specific sentiment words that are indicative of a particular rating.

Learning Attitudes and Attributes from Multi-Aspect Reviews

This paper describes a fully automatic two-stage machine learning architecture that learns temporal relations between pairs of events. The first stage learns the temporal attributes of single event descriptions, such as tense, grammatical aspect, and aspectual class. These imperfect guesses, combined with other linguistic features, are then used in a second stage to classify the temporal relationship between two events. We present both an analysis of our new features and results on the TimeBank Corpus that is 3% higher than previous work that used perfect human tagged features.

/pdf/classifying-temporal-relations-between-events-1wihffkuyq.pdf

Classifying Temporal Relations Between Events

Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities However, an open challenge in this area is developing techniques that can go beyond simple edge prediction and handle more complex logical queries, which might involve multiple unobserved edges, entities, and variables For instance, given an incomplete biological knowledge graph, we might want to predict "em what drugs are likely to target proteins involved with both diseases X and Y?" -- a query that requires reasoning about all possible proteins that might interact with diseases X and Y Here we introduce a framework to efficiently make predictions about conjunctive logical queries -- a flexible but tractable subset of first-order logic -- on incomplete knowledge graphs In our approach, we embed graph nodes in a low-dimensional space and represent logical operators as learned geometric operations (eg, translation, rotation) in this embedding space By performing logical operations within a low-dimensional embedding space, our approach achieves a time complexity that is linear in the number of query variables, compared to the exponential complexity required by a naive enumeration-based approach We demonstrate the utility of this framework in two application studies on real-world datasets with millions of relations: predicting logical relationships in a network of drug-gene-disease interactions and in a graph-based representation of social interactions derived from a popular web forum

/pdf/embedding-logical-queries-on-knowledge-graphs-25x9ytpejs.pdf

Embedding Logical Queries on Knowledge Graphs

This paper describes a recently completed common resource for the study of spoken discourse, the NXT-format Switchboard Corpus. Switchboard is a long-standing corpus of telephone conversations (Godfrey et al. in SWITCHBOARD: Telephone speech corpus for research and development. In Proceedings of ICASSP-92, pp. 517---520, 1992). We have brought together transcriptions with existing annotations for syntax, disfluency, speech acts, animacy, information status, coreference, and prosody; along with substantial new annotations of focus/contrast, more prosody, syllables and phones. The combined corpus uses the format of the NITE XML Toolkit, which allows these annotations to be browsed and searched as a coherent set (Carletta et al. in Lang Resour Eval J 39(4):313---334, 2005). The resulting corpus is a rich resource for the investigation of the linguistic features of dialogue and how they interact. As well as describing the corpus itself, we discuss our approach to overcoming issues involved in such a data integration project, relevant to both users of the corpus and others in the language resource community undertaking similar projects.

/pdf/the-nxt-format-switchboard-corpus-a-rich-resource-for-90wdm033sw.pdf

Dan Jurafsky

Papers

Probabilistic Modeling in Psycholinguistics: Linguistic Comprehension and Production

Learning Attitudes and Attributes from Multi-Aspect Reviews

Classifying Temporal Relations Between Events

Embedding Logical Queries on Knowledge Graphs

The NXT-format Switchboard Corpus: a rich resource for investigating the syntax, semantics, pragmatics and prosody of dialogue