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

Before beginning the research that led to "Probabilistic logic" [11 ], I had participated with Richard Duda, Peter Hart, and Georgia Sutherland on the PROSPECTOR project [3]. There, we used Bayes' rule (with some assumptions about conditional independence) to deduce the probabilities of hypotheses about ore deposits given (sometimes uncertain) geologic evidence collected in the field [4]. At that time, I was also familiar with the use of "certainty factors" by Shortliffe [18], the use of "fuzzy logic" by Zadeh [20], and the Dempster/Shafer formalism [16]. All of these methods made (sometimes implicit and unacknowledged) assumptions about underlying joint probability distributions, and I wanted to know how the mathematics would work out if no such assumptions were made. I began by asking how modus ponens would generalize when one assigned probabilities (instead of binary truth values) to P and P D Q. As can be verified by simple calculations using a Venn diagram, the probability of Q is under-determined in this case but can be bounded as follows:

/pdf/probabilistic-logic-revisited-447wkfkqap.pdf

Probabilistic logic revisited

We analyze problems confronted by computer agents that synthesize plans that take into account (and employ) the plans of other, similar, cooperative agents. From the point of view of each of these agents, the others are dynamic entities that possess information about the world, have goals, make plans to achieve these goals, and execute these plans. Thus, each agent must represent not only the usual information about objects in the world and the preconditions and effects of its own actions, but it must also represent and reason about what other agents believe and what they may do. We describe a planning system that addresses these issues and show how it solves a sample problem.

/pdf/multiple-agent-planning-systems-ah4du6xqe8.pdf

Multiple-agent planning systems

: For the past several years research on robot problem-solving methods has centered on what may one day be called simple plans: linear sequences of actions to be performed by single robots to achieve single goals in static environments. Recent speculation and preliminary work at several research centers has suggested a variety of ways in which these traditional constraints could be relaxed. In this paper we describe some of these possible extensions, illustrating the discussion where possible with examples taken from the current Stanford Research Institute robot system.

Some New Directions in Robot Problem Solving

In its early stages, the field of AI had as its main goal the invention of computer programs having the general problem-solving abilities of humans. Along the way, a major shift of emphasis developed from general-purpose programs toward performance programs, ones whose competence was highly specialized and limited to particular areas of expertise. In this article, I claim that AI is now at the beginning of another transition, one that will reinvigorate efforts to build programs of general, humanlike competence. These programs will use specialized performance programs as tools, much like humans do.

Eye on the prize

I analyze some of the attacks against the Physical Symbol System Hypothesis--attacks based on the presumed need for symbol-grounding and non-symbolic processing for intelligent behavior and on the supposed non-computational and "mindless" aspects of brains.

/pdf/the-physical-symbol-system-hypothesis-status-and-prospects-2bmvvplyne.pdf

Nils J. Nilsson

Papers

Probabilistic logic revisited

Multiple-agent planning systems

Some New Directions in Robot Problem Solving

Eye on the prize

The physical symbol system hypothesis: status and prospects