This book stresses the use of learning, and in particular perceptual learning, to develop thinking entities.

This book stresses the use of learning, and in particular perceptual learning, to develop thinking entities.

Statistical pattern recognition; Probability density estimation; Single-layer networks; The multi-layer perceptron; Radial basis functions; Error functions; Parameter optimization algorithms; Pre-processing and feature extraction; Learning and generalization; Bayesian techniques; Appendix; References; Index.

What happens when we think? How do people make judgments? While different theories abound—and are heatedly debated—most are based on an algorithmic model of how the brain works. Howard Margolis builds a fascinating case for a theory that thinking is based on recognizing patterns and that this process is intrinsically a-logical. Margolis gives a Darwinian account of how pattern recognition evolved to reach human cognitive abilities. Illusions of judgment—standard anomalies where people consistently misjudge or misperceive what is logically implied or really present—are often used in cognitive science to explore the workings of the cognitive process. The explanations given for these anomalous results have generally explained only the anomaly under study and nothing more. Margolis provides a provocative and systematic analysis of these illusions, which explains why such anomalies exist and recur. Offering empirical applications of his theory, Margolis turns to historical cases to show how an individual's cognitive repertoire—the available cognitive patterns and their relation to cues—changes or resists changes over time. Here he focuses on the change in worldview occasioned by the Copernican discovery: not only how an individual might come to see things in a radically new way, but how it is possible for that new view to spread and become the dominant one. A reanalysis of the trial of Galileo focuses on social cognition and its interactions with politics. In challenging the prevailing paradigm for understanding how the human mind works, Patterns, Thinking, and Cognition is certain to stimulate fruitful debate.

'Part-detective story, part-cultural snapshot . . . all bound by Gibson's pin-sharp prose' Arena -------------- THE FIRST NOVEL IN THE BLUE ANT TRILIOGY - READ ZERO HISTORY AND SPOOK COUNTRY FOR MORE Cayce Pollard has a new job. She's been offered a special project: track down the makers of an addictive online film that's lighting up the internet. Hunting the source will take her to Tokyo and Moscow and put her in the sights of Japanese hackers and Russian Mafia. She's up against those who want to control the film, to own it - who figure breaking the law is just another business strategy. The kind of people who relish turning the hunter into the hunted . . . A gripping spy thriller by William Gibson, bestselling author of Neuromancer. Part prophesy, part satire, Pattern Recognition skewers the absurdity of modern life with the lightest and most engaging of touches. Readers of Neal Stephenson, Ray Bradbury and Iain M. Banks won't be able to put this book down. -------------- 'Fast, witty and cleverly politicized' Guardian 'A big novel, full of bold ideas . . . races along like an expert thriller' GQ 'Dangerously hip. Its dialogue and characterization will amaze you. A wonderfully detailed, reckless journey of espionage and lies' USA Today 'A compelling, humane story with a sympathetic heroine searching for meaning and consolation in a post-everything world' Daily Telegraph 'Electric, profound. Gibson's descriptions of Tokyo, Russia and London are surreally spot-on' Financial Times

This is the first textbook on pattern recognition to present the Bayesian viewpoint. The book presents approximate inference algorithms that permit fast approximate answers in situations where exact answers are not feasible. It uses graphical models to describe probability distributions when no other books apply graphical models to machine learning. No previous knowledge of pattern recognition or machine learning concepts is assumed. Familiarity with multivariate calculus and basic linear algebra is required, and some experience in the use of probabilities would be helpful though not essential as the book includes a self-contained introduction to basic probability theory.

The fundamental mathematical tools needed to understand machine learning include linear algebra, analytic geometry, matrix decompositions, vector calculus, optimization, probability and statistics. These topics are traditionally taught in disparate courses, making it hard for data science or computer science students, or professionals, to efficiently learn the mathematics. This self-contained textbook bridges the gap between mathematical and machine learning texts, introducing the mathematical concepts with a minimum of prerequisites. It uses these concepts to derive four central machine learning methods: linear regression, principal component analysis, Gaussian mixture models and support vector machines. For students and others with a mathematical background, these derivations provide a starting point to machine learning texts. For those learning the mathematics for the first time, the methods help build intuition and practical experience with applying mathematical concepts. Every chapter includes worked examples and exercises to test understanding. Programming tutorials are offered on the book's web site.