Common LISP modules: artificial intelligence in the era of neural networks and chaos theory
This entertaining book is designed for the reader who enjoys thinking about new technologies and how to use them in solving practical problems. It provides reusable software modules for specific applications, as well as the methodology and spirit required to master problems for which there is no obvious solution. This book is for AI novices who want to learn new technologies and increase their capabilities and for AI professionals who want reusable application-oriented software modules to use in building their own systems. Each chapter contains background information and theory, a discussion of sample programs, program listings and output, additional information on the sample programs, and suggested exercises. Chapters use engaging real-world examples such as speech and handwriting recognition using neural networks, natural language processing with an example database interface, expert system shells, computer chess game, chaos theory, and fractal generation programs. The text assumes a reading knowledge of LISP and the implementation ability of a set of graphics primitives used for simple graphics operations. While all examples are implemented in Common LISP, the examples are also portable to other LISP dialects. The neural network and fractal examples are also portable to other languages such as C and Pascal.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Introduction and Device Independent Graphics
Artificial Neural Networks
Pattern Recognition Using Hopfield Neural Networks
12 other sections not shown
&aux activation energy array array-dimension ART2 BP BP BP breadth-first search cadr calculate Chaos theory chapter chess Common LISP cons list database defined defun delta rule neural delta weights deltaRecall dmax dolist dotimes equal aref board example program execute expert-system FactList Figure fileStream function global variable graphics window heuristic Hopfield network iDimension input neurons input pattern isAdj jeep lambda layer leave jeep make-array list Mandelbrot set Mark Watson member word move natural language netList NewDeltaNetwork nLayers nlnputs noun num-inputs numlnputs numOutputs output neurons parser parsing path piece plot plot-line plot-string-italic prepp princ program listing reset returned RMS error rule neural network sample semantic Semantic memory setf aref board setq retVal Sigmoid Sigmoid function sizeList slab speech recognition square squareNum static evaluation terpri theNetwork training data training examples training-list truncate w-list WP WP XSCALE xsize ysize