Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability. The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

/pdf/reinforcement-learning-an-introduction-rzxgej9p17.pdf

Reinforcement Learning: An Introduction

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

Computational properties of use of biological organisms or to the construction of computers can emerge as collective properties of systems having a large number of simple equivalent components (or neurons). The physical meaning of content-addressable memory is described by an appropriate phase space flow of the state of a system. A model of such a system is given, based on aspects of neurobiology but readily adapted to integrated circuits. The collective properties of this model produce a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size. The algorithm for the time evolution of the state of the system is based on asynchronous parallel processing. Additional emergent collective properties include some capacity for generalization, familiarity recognition, categorization, error correction, and time sequence retention. The collective properties are only weakly sensitive to details of the modeling or the failure of individual devices.

https://www.pnas.org/content/pnas/79/8/2554.full.pdf

Neural networks and physical systems with emergent collective computational abilities

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

Deep learning in neural networks

The concept of a linguistic variable and its application to approximate reasoning—II☆

: A partial theory is presented of thinking, combining a number of classical and modern concepts from psychology, linguistics, and AI. In a new situation one selects from memory a structure called a frame: a remembered framework to be adapted to fit reality by changing details as necessary, and a data-structure for representing a stereotyped situation. Attached to each frame are several kinds of information -- how to use the frame, what one can expect to happen next, and what to do if these expectations are not confirmed. The report discusses collections of related frames that are linked together into frame-systems.

/pdf/a-framework-for-representing-knowledge-4ptb6mi5zb.pdf

A framework for representing knowledge

Briefly describes frame systems as a formalism for representing knowledge and then concentrates on the issue of what the content of knowledge should be in specific domains. Argues that vision should be viewed symbolically with an emphasis on forming expectations and then using details to fill in slots in those expectations. Discusses the enormous problem of the volume of background common sense knowledge required to understand even very simple natural language texts and suggests that networks of frames are a reasonable approach to represent such knowledge. Discusses the concept of expectation further including ways to adapt to and understand expectation failures. Argues that numerical approaches to knowledge representation are inherently limited.

Marvin Minsky--one of the fathers of computer science and cofounder of the Artificial Intelligence Laboratory at MIT--gives a revolutionary answer to the age-old question: "how does the mind work?"

https://www.jstor.org/stable/pdfplus/20708493.pdf

The Society of Mind

Cambridge, Mass.: MIT Press, 1972. 2nd. ed. The book's aim is to seek general results from the close study of abstract version of devices known as perceptrons

Perceptrons: An Introduction to Computational Geometry

From the Preface (See Front Matter for full Preface)

Man has within a single generation found himself sharing the world with a strange new species: the computers and computer-like machines. Neither history, nor philosophy, nor common sense will tell us how these machines will affect us, for they do not do "work" as did machines of the Industrial Revolution. Instead of dealing with materials or energy, we are told that they handle "control" and "information" and even "intellectual processes." There are very few individuals today who doubt that the computer and its relatives are developing rapidly in capability and complexity, and that these machines are destined to play important (though not as yet fully understood) roles in society's future. Though only some of us deal directly with computers, all of us are falling under the shadow of their ever-growing sphere of influence, and thus we all need to understand their capabilities and their limitations.

It would indeed be reassuring to have a book that categorically and systematically described what all these machines can do and what they cannot do, giving sound theoretical or practical grounds for each judgment. However, although some books have purported to do this, it cannot be done for the following reasons: a) Computer-like devices are utterly unlike anything which science has ever considered---we still lack the tools necessary to fully analyze, synthesize, or even think about them; and b) The methods discovered so far are effective in certain areas, but are developing much too rapidly to allow a useful interpretation and interpolation of results. The abstract theory---as described in this book---tells us in no uncertain terms that the machines' potential range is enormous, and that its theoretical limitations are of the subtlest and most elusive sort. There is no reason to suppose machines have any limitations not shared by man.

Marvin Minsky

Papers

A framework for representing knowledge

A framework for representing knowledge

The Society of Mind

Perceptrons: An Introduction to Computational Geometry

Computation: Finite and Infinite Machines