McGraw-Hill, 1991 - 621 páginas
The breadth of A. I. is explored and explained in this best selling text. Assuming no prior knowledge,it covers topics like neural networks and robotics. This text explores the range of problems which have been and remain to be solved using A. I. tools and techniques. The second half of this text is an excellent reference.
Resultados 1-3 de 23
This gives us a way of characterizing how good a set of weights is. Let w be the
weight vector (vt'o, w\ , . . . , w„), and let X be the subset of training instances
misclassified by the current set of weights. Then define the perceptron criterion ...
Like a perceptron, a backpropagation network typically starts out with a random
set of weights. The network adjusts its weights each time it sees an input-output
pair. Each pair requires two stages: a forward pass and a backward pass.
Algorithm: Competitive Learning Given: A network consisting of n binary-valued
input units directly connected to any number of output units. Produce: A set of
weights such that the output units become active according to some natural
Comentarios de la gente - Escribir un comentario
Calificaciones de los usuarios
very poor book for novice.Assumes u already know AI and the language is not at all user friendly.One has to read a sentence repeatedly to get a grasp and some times even then u don't understand.Go for other books much better than this
not soo good to go for novice
What Is Artificial Intelligence?
Problems Problem Spaces and Search
Heuristic Search Techniques
Derechos de autor
Otras 21 secciones no mostradas