From the Publisher:
Probabilistic Reasoning in Intelligent Systems is a complete andaccessible account of the theoretical foundations and computational methods that underlie plausible reasoning under uncertainty. The author provides a coherent explication of probability as a language for reasoning with partial belief and offers a unifying perspective on other AI approaches to uncertainty, such as the Dempster-Shafer formalism, truth maintenance systems, and nonmonotonic logic. The author distinguishes syntactic and semantic approaches to uncertaintyand offers techniques, based on belief networks, that provide a mechanism for making semantics-based systems operational. Specifically, network-propagation techniques serve as a mechanism for combining the theoretical coherence of probability theory with modern demands of reasoning-systems technology: modular declarative inputs, conceptually meaningful inferences, and parallel distributed computation. Application areas include diagnosis, forecasting, image interpretation, multi-sensor fusion, decision support systems, plan recognition, planning, speech recognitionin short, almost every task requiring that conclusions be drawn from uncertain clues and incomplete information.
Probabilistic Reasoning in Intelligent Systems will be of special interest to scholars and researchers in AI, decision theory, statistics, logic, philosophy, cognitive psychology, and the management sciences. Professionals in the areas of knowledge-based systems, operations research, engineering, and statistics will find theoretical and computational tools of immediate practical use. The book can also be used as an excellent text for graduate-level courses in AI, operations research, or applied probability.

Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference

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

Deep learning in neural networks

Background on genetic algorithms, LISP, and genetic programming hierarchical problem-solving introduction to automatically-defined functions - the two-boxes problem problems that straddle the breakeven point for computational effort Boolean parity functions determining the architecture of the program the lawnmower problem the bumblebee problem the increasing benefits of ADFs as problems are scaled up finding an impulse response function artificial ant on the San Mateo trail obstacle-avoiding robot the minesweeper problem automatic discovery of detectors for letter recognition flushes and four-of-a-kinds in a pinochle deck introduction to biochemistry and molecular biology prediction of transmembrane domains in proteins prediction of omega loops in proteins lookahead version of the transmembrane problem evolutionary selection of the architecture of the program evolution of primitives and sufficiency evolutionary selection of terminals evolution of closure simultaneous evolution of architecture, primitive functions, terminals, sufficiency, and closure the role of representation and the lens effect Appendices: list of special symbols list of special functions list of type fonts default parameters computer implementation annotated bibliography of genetic programming electronic mailing list and public repository

Genetic Programming: On the Programming of Computers by Means of Natural Selection

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

A translation approach to portable ontology specifications

Our paper on the use of heuristic information in graph searching defined a path-finding algorithm, A*, and proved that it had two important properties. In the notation of the paper, we proved that if the heuristic function n (n) is a lower bound on the true minimal cost from node n to a goal node, then A* is admissible; i.e., it would find a minimal cost path if any path to a goal node existed. Further, we proved that if the heuristic function also satisfied something called the consistency assumption, then A* was optimal; i.e., it expanded no more nodes than any other admissible algorithm A no more informed than A*. These results were summarized in a book by one of us.

Correction to "A Formal Basis for the Heuristic Determination of Minimum Cost Paths"

Artificial intelligence (AI) is a field within computer science that is attempting to build enhanced intelligence into computer systems. This book traces the history of the subject, from the early dreams of eighteenth-century (and earlier) pioneers to the more successful work of today's AI engineers. AI is becoming more and more a part of everyone's life. The technology is already embedded in face-recognizing cameras, speech-recognition software, Internet search engines, and health-care robots, among other applications. The book's many diagrams and easy-to-understand descriptions of AI programs will help the casual reader gain an understanding of how these and other AI systems actually work. Its thorough (but unobtrusive) end-of-chapter notes containing citations to important source materials will be of great use to AI scholars and researchers. This book promises to be the definitive history of a field that has captivated the imaginations of scientists, philosophers, and writers for centuries.

The Quest for Artificial Intelligence

http://ai.stanford.edu/~nilsson/OnlinePubs-Nils/PublishedPapers/logicai.pdf

Logic and artificial intelligence

We describe a new problem solver called STRIPS that attempts to find a sequence of operators in a space of world models to transform a given initial world model into a model in which a given goal formula can be proven to be true. STRIPS represents a world model as an arbi trary collection of first-order predicate calculus formulas and is designed to work with models consisting of large numbers of formulas. It employs a resolution theorem prover to answer (juestions of particular models and uses means-ends analysis to guide it to the desired goal-satisfying model.

/pdf/strips-a-new-approach-to-the-application-of-theorem-proving-6a4vpb6nqv.pdf

STRIPS: a new approach to the application of theorem proving to problem solving

This book is about machines that learn to discover hidden relationships in data. A constant sfream of data bombards our senses and millions of sensory channels carry information into our brains. Brains are also learning machines that condition, combine, parse, and store data. Is it possible to learn something about learning by observing the style of computation used by brains? This is the motivation for research into computational devices that today are called "neural networks." Neural networks are nonlinear dynamical systems with many degrees of freedom that can be used to solve computational problems. The mathematical foundations for learning in this class of machines was laid by agroup of researchers in the 1940s and 1950s. The achievement documented in this book is the thorough study of one of the simplest members of this class, feedforward networks with one layer of m w ~ a b l e weights connecting input units to output units. In a sense, these might be called reflex machines. The knee-jerk reflex, for example, is mediated by synaptic connections from the sensory recepton in your knee directly onto rnotoneurons in your spinal cord that in turn activate leg muscles. There are limits to how much computation can be accomplished by such reflexes, and these limits have been carefully delineated in this book. Just as more complex creatures evolved by layering control loops on the primitive reflexes, network models have also evolved in recent years and now have achieved vastly greater capabilities than reflex machines by making use of multilayered architectures with feedback connections. Nonetheless, recent work could not have been accomplished without building on these foundations. vii viil INTRODUCTION INTRODUCTION ix Despite the early promise of research on neural networks, there was a period of about 20 years, from the mid 1960s to the mid 1980s. when interest in neural networks as computational devices and models of human behavior waned in favor of models based on symbol processing. There are many reasons for this, some of them now evident in this book. Still, Learning Machines was an underground classic among the neural network modelers who were active during this "dark age" and deserves to be better known to the generation that is "relearning" what was once known about statistical learning machines. The intuitive geometric explanations and the mathematical foundations in this monograph are as invaluable today as they were when it was first written. Nilsson is …

Nils J. Nilsson

Papers

Correction to "A Formal Basis for the Heuristic Determination of Minimum Cost Paths"

The Quest for Artificial Intelligence

Logic and artificial intelligence

STRIPS: a new approach to the application of theorem proving to problem solving

The Mathematical Foundations of Learning Machines