A tutorial is presented describing a general machine learning theory which spawns a class of energy minimizing machines useful in model identification, optimization, and associative memory. Special realizations of the theory include the Boltzmann machine and the Hopfield neural network. The theory is reinforced by appendices addressing particular facets of the machine, ranging from gradient descent to simulated annealing. The treatment is systematic, beginning with the description of the energy function. A defining relationship is established between the energy function and the optimal solution. Following, both classical and new learning algorithms are presented (directing the adaption of the free parameters) for numerically minimizing such function to yield the optimal solution. Finally, both computational burden and performance are assessed for several small-scale applications to date. Keywords: Neural networks, Boltzmann machine, Gibbs machine, Energy minimizing neural networks, Simulated annealing. (jhd).
"One hundred years ago, the fundamental building block of the central nervous system, the neuron, was discovered. This study focuses on the existing mathematical models of neurons and their interactions, the simulation of which has been one of the biggest challenges facing modern science." "More than fifty years ago, W. S. McCulloch and W. Pitts devised their model for the neuron, John von Neumann seemed to sense the possibilities for the development of intelligent systems, and Frank Rosenblatt came up with a functioning network of neurons. Despite these advances, the subject had begun to fade as a major research area until John Hopfield arrived on the scene. Drawing an analogy between neural networks and the Ising spin models of ferromagnetism, Hopfield was able to introduce a "computational energy" that would decline toward stable minima under the operation of the system of neurodynamics devised by Roy Glauber." "Like a switch, a neuron is said to be either "on" or "off." The state of the neuron is determined by the states of the other neurons and the connections between them, and the connections are assumed to be reciprocal - that is, neuron number one influences neuron number two exactly as strongly as neuron number two influences neuron number one. According to the Glauber dynamics, the states of the neurons are updated in a random serial way until an equilibrium is reached. An energy function can be associated with each state, and equilibrium corresponds to a minimum of this energy. It follows from Hopfield's assumption of reciprocity that an equilibrium will always be reached." "D. H. Ackley, G. E. Hinton, and T. J. Sejnowski modified the Hopfield network by introducing the simulated annealing algorithm to search out the deepest minima. This is accomplished by - loosely speaking - shaking the machine. The violence of the shaking is controlled by a parameter called temperature, producing the Boltzmann machine - a name designed to emphasize the connection to the statistical physics of Ising spin models." "The Boltzmann machine reduces to the Hopfield model in the special case where the temperature goes to zero. The resulting network, under the Glauber dynamics, produces a homogeneous, irreducible, aperiodic Markov chain as it wanders through state space. The entire theory of Markov chains becomes applicable to the Boltzmann machine." "With ten chapters, five appendices, a list of references, and an index, this study should serve as an introduction to the field of neural networks and its application, and is suitable for an introductory graduate course or an advanced undergraduate course."--BOOK JACKET.Title Summary field provided by Blackwell North America, Inc. All Rights Reserved
This volume represents the state of the art for much current research in many-valued logics. Primary researchers in the field are among the authors. Major methodological issues of many-valued logics are treated, as well as applications of many-valued logics to reasoning with fuzzy information. Areas covered include: Algebras of multiple valued logics and their applications, proof theory and automated deduction in multiple valued logics, fuzzy logics and their applications, and multiple valued logics for control theory and rational belief.
This book is a printed edition of the Special Issue "Short-Term Load Forecasting by Artificial Intelligent Technologies" that was published in Energies
Students with diverse backgrounds will face a multitude of decisions in a variety of engineering, scientific, industrial, and financial settings. They will need to know how to identify problems that the methods of operations research (OR) can solve, how to structure the problems into standard mathematical models, and finally how to apply or develop computational tools to solve the problems. Perfect for any one-semester course in OR, Operations Research: A Practical Introduction answers all of these needs. In addition to providing a practical introduction and guide to using OR techniques, it includes a timely examination of innovative methods and practical issues related to the development and use of computer implementations. It provides a sound introduction to the mathematical models relevant to OR and illustrates the effective use of OR techniques with examples drawn from industrial, computing, engineering, and business applications. Many students will take only one course in the techniques of Operations Research. Operations Research: A Practical Introduction offers them the greatest benefit from that course through a broad survey of the techniques and tools available for quantitative decision making. It will also encourage other students to pursue more advanced studies and provides you a concise, well-structured, vehicle for delivering the best possible overview of the discipline.
