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 increasing volume of data in modern business and science calls for more complex and sophisticated tools. Although advances in data mining technology have made extensive data collection much easier, it's still always evolving and there is a constant need for new techniques and tools that can help us transform this data into useful information and knowledge. Since the previous edition's publication, great advances have been made in the field of data mining. Not only does the third of edition of Data Mining: Concepts and Techniques continue the tradition of equipping you with an understanding and application of the theory and practice of discovering patterns hidden in large data sets, it also focuses on new, important topics in the field: data warehouses and data cube technology, mining stream, mining social networks, and mining spatial, multimedia and other complex data. Each chapter is a stand-alone guide to a critical topic, presenting proven algorithms and sound implementations ready to be used directly or with strategic modification against live data. This is the resource you need if you want to apply today's most powerful data mining techniques to meet real business challenges. * Presents dozens of algorithms and implementation examples, all in pseudo-code and suitable for use in real-world, large-scale data mining projects. * Addresses advanced topics such as mining object-relational databases, spatial databases, multimedia databases, time-series databases, text databases, the World Wide Web, and applications in several fields. *Provides a comprehensive, practical look at the concepts and techniques you need to get the most out of real business data

/pdf/data-mining-concepts-and-techniques-4dtvdfkvmi.pdf

Data Mining: Concepts and Techniques

https://www2.econ.iastate.edu/tesfatsi/DeepLearningInNeuralNetworksOverview.JSchmidhuber2015.pdf

Deep learning in neural networks

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

1. Introduction to probabilities, graphs, and causal models 2. A theory of inferred causation 3. Causal diagrams and the identification of causal effects 4. Actions, plans, and direct effects 5. Causality and structural models in the social sciences 6. Simpson's paradox, confounding, and collapsibility 7. Structural and counterfactual models 8. Imperfect experiments: bounds and counterfactuals 9. Probability of causation: interpretation and identification Epilogue: the art and science of cause and effect.

Causality: models, reasoning, and inference

Modeling subjective uncertainty in image annotation

This chapter is written for computer scientists, engineers, mathematicians, and scientists who wish to gain a better understanding of the role of statistical thinking in modern data mining. Data mining has attracted considerable attention both in the research and commercial arenas in recent years, involving the application of a variety of techniques from both computer science and statistics. The chapter discusses how computer scientists and statisticians approach data from different but complementary viewpoints and highlights the fundamental differences between statistical and computational views of data mining. In doing so we review the historical importance of statistical contributions to machine learning and data mining, including neural networks, graphical models, and flexible predictive modeling. The primary conclusion is that closer integration of computational methods with statistical thinking is likely to become increasingly important in data mining applications.

https://link.springer.com/content/pdf/10.1007%2F978-1-4615-1733-7_3.pdf

Data Mining at the Interface of Computer Science and Statistics

Statistical topic models provide a general data-driven fra mework for automated discovery of highlevel knowledge from large collections of text documents. While topic models can potentially discover a broad range of themes in a data set, the interpretabil ity of the learned topics is not always ideal. Human-defined concepts, on the other hand, tend to be s emantically richer due to careful selection of words to define concepts but they tend not to cover t he themes in a data set exhaustively. In this paper, we propose a probabilistic framework to combine a hierarchy of human-defined semantic concepts with statistical topic models to seek the best of both worlds. Experimental results using two different sources of concept hierarchies and two collections of text documents indicate that this combination leads to systematic improvements in the quality of the associated language models as well as enabling new techniques for inferring and visualizing the semantics of a document.

https://www.ics.uci.edu/~chandra/pubs/hctmtechreport.pdf

Text Modeling using Unsupervised Topic Models and Concept Hierarchies

A high-speed distortionless predictive image-compression scheme that is based on differential pulse code modulation output modeling combined with efficient source-code design is introduced. Experimental results show that this scheme achieves compression that is very close to the difference entropy of the source.

/pdf/a-high-speed-distortionless-predictive-image-compression-1ewx1q1jok.pdf

A High-Speed Distortionless Predictive Image-Compression Scheme

Interactive querying of massive data sets is an increasingly important application in the fields like interactive data mining, exploratory data analysis, prediction of customer behaviour and optimization of database management systems (DBMS). Formally, the task can be formulated as follows: given a binary transaction data set and a query on a subset of its attributes, find (predict) the probability that a randomly selected data record satisfies the query. A straightforward solution of scanning the data directly does not scale up to typical transaction data sets that are huge in a data mining sense. Although fast, memory efficient and one of the most popular solutions in commercial DBMS, the independence model has long been criticized for often being quite inaccurate. Other techniques proposed in the literature suffer from the curse of dimensionality and are practical only for low-dimensional data sets. 
In this dissertation, we develop a number of novel probabilistic approaches to the querying problem. Unlike previously proposed methods our techniques satisfy the following requirements: (a) they work on high-dimensional binary transaction data, and (b) they allow the user to effectively trade accuracy in the estimates for query execution time and memory taken by the model. We empirically explore the tradeoffs in terms of accuracy, time and memory offered by these models and establish that the choice of the best-performing model for any particular querying situation depends on a variety of factors, such as the density of the data and the distribution of user queries. We illustrate that no single model universally dominates. 
This naturally leads to the question of how to automatically determine which approximation model is optimal for any given situation. To resolve this question, we leverage recent results in the machine learning and statistics literature that show that combinations of models can outperform any single model for prediction tasks. Specifically, for query approximation, we propose a data-adaptive technique for combining probabilistic query approximation models. We demonstrate that on real-world and simulated data sets the combined model can reduce the error of any single model by factors of up to 50%. Furthermore, we demonstrate how time and memory constraints can be easily incorporated into the model-combining algorithm. Adapting the model is a straightforward and scalable optimization problem that can be completely automated, providing a practical and query-adaptive framework for online query approximation.

Padhraic Smyth

Papers

Modeling subjective uncertainty in image annotation

Data Mining at the Interface of Computer Science and Statistics

Text Modeling using Unsupervised Topic Models and Concept Hierarchies

A High-Speed Distortionless Predictive Image-Compression Scheme

Probabilistic query models for transaction data