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

In this dissertation, we consider the problem of modeling grouped data where individual group members share common characteristic patterns but with some random variation. The first problem of this type we investigate is waveform modeling and classification, where waveforms consist of sets of measurements of a phenomena over time (such as an ECG trace of a heartbeat). The second problem we investigate involves analyzing spatial patterns in groups of images, such as brain activation images obtained from functional magnetic resonance imaging (fMRI). In both cases we model the shape of waveforms and activation patterns explicitly using probabilistic models that parameterize the shape information directly. We incorporate random effects models to handle variability in shape parameters across different waveforms or images. The random effects model allows each group to have its own shape parameters that are modeled as coming from a common prior distribution that can be viewed as a shape template. We develop learning algorithms for these models that can learn both the template and group-specific shapes. We use real-world waveform and imaging data to demonstrate the advantages of the proposed models.

Learning hierarchical probabilistic models with random effects with applications to time-series and image data

Improving our understanding of how humans perceive AI teammates is an important foundation for our general understanding of human-AI teams. Extending relevant work from cognitive science, we propose a framework based on item response theory for modeling these perceptions. We apply this framework to real-world experiments, in which each participant works alongside another person or an AI agent in a question-answering setting, repeatedly assessing their teammate’s performance. Using this experimental data, we demonstrate the use of our framework for testing research questions about people’s perceptions of both AI agents and other people. We contrast mental models of AI teammates with those of human teammates as we characterize the dimensionality of these mental models, their development over time, and the influence of the participants’ own self-perception. Our results indicate that people expect AI agents’ performance to be significantly better on average than the performance of other humans, with less variation across different types of problems. We conclude with a discussion of the implications of these findings for human-AI interaction.

/pdf/capturing-humans-mental-models-of-ai-an-item-response-theory-2f57pp79.pdf

Capturing Humans’ Mental Models of AI: An Item Response Theory Approach

Advances in the use of autoregressive models, pattern recognition methods, and hidden Markov models for on-line health monitoring of dynamic systems (such as DSN antennas) have recently been reported. However, the algorithms described in previous work have the significant drawback that data acquired under fault conditions are assumed to be available in order to train the model used for monitoring the system under observation. This article reports that this assumption can be relaxed and that hidden Markov monitoring models can be constructed using only data acquired under normal conditions and prior knowledge of the system characteristics being measured. The method is described and evaluated on data from the DSS 13 34-m beam wave guide antenna. The primary conclusion from the experimental results is that the method is indeed practical and holds considerable promise for application at the 70-m antenna sites where acquisition of fault data under controlled conditions is not realistic.

Failure monitoring in dynamic systems: Model construction without fault training data

We expose the statistical foundations of deep learning with the goal of facilitating conversation between the deep learning and statistics communities. We highlight core themes at the intersection; summarize key neural models, such as feedforward neural networks, sequential neural networks, and neural latent variable models; and link these ideas to their roots in probability and statistics. We also highlight research directions in deep learning where there are opportunities for statistical contributions.

https://www.annualreviews.org/doi/pdf/10.1146/annurev-statistics-032921-013738

A Brief Tour of Deep Learning from a Statistical Perspective

The results of applying pattern recognition techniques to diagnose fault conditions in the pointing system of one of the Deep Space network's large antennas, the DSS 13 34-meter structure, are discussed. A previous article described an experiment whereby a neural network technique was used to identify fault classes by using data obtained from a simulation model of the Deep Space Network (DSN) 70-meter antenna system. Described here is the extension of these classification techniques to the analysis of real data from the field. The general architecture and philosophy of an autonomous monitoring paradigm is described and classification results are discussed and analyzed in this context. Key features of this approach include a probabilistic time-varying context model, the effective integration of signal processing and system identification techniques with pattern recognition algorithms, and the ability to calibrate the system given limited amounts of training data. Reported here are recognition accuracies in the 97 to 98 percent range for the particular fault classes included in the experiments.

Padhraic Smyth

Papers

Learning hierarchical probabilistic models with random effects with applications to time-series and image data

Capturing Humans’ Mental Models of AI: An Item Response Theory Approach

Failure monitoring in dynamic systems: Model construction without fault training data

A Brief Tour of Deep Learning from a Statistical Perspective

Pattern-recognition techniques applied to performance monitoring of the DSS 13 34-meter antenna control assembly