What people are saying - Write a review
We haven't found any reviews in the usual places.
Principles and promises
The McCulloch and Pitts legacy
The hard learning problem
12 other sections not shown
Other editions - View all
2-input achieved action activation analysis applied association units assumed autoassociative back-propagation behaviour binary Boltzmann machines brain calculated Carver Mead Chapter chip clamped cognitive column connection strengths content-addressable memory conventional computing delta rule described detection device diagram discriminator discussed energy equal probability equation error back-propagation example feed-forward feedback firing rule fully connected function Hamming distance hidden units Hinton Hopfield inequality input pattern input units layer learning rule Markov chain McCulloch and Pitts MCP model MCP node memory method minima Neocognitron neural computing neural nets neural system neuron number of inputs oiab output unit overall overlap parity perceptron phonemes possible properties pyramid RAM-neuron RAMs firing recognition response Rumelhart scheme seen sensory shown in fig stable stored synapses synchronous task techniques temperature threshold training patterns training set transition truth table unsupervised learning values weights WISARD