Ann 1 Slides PDF

Artificial Neural Networks ANN’s Artificial neural network (ANN): Alternative to Physical symbol system Neural networks are models of information-processing at the algorithmic level not implementations of symbolic algorithms PSSH vs. Connectionism The physical symbol system hypo...

Artificial Neural Networks ANN’s Artificial neural network (ANN): Alternative to Physical symbol system Neural networks are models of information-processing at the algorithmic level not implementations of symbolic algorithms PSSH vs. Connectionism The physical symbol system hypothesis: a physical symbol system has the necessary and sufficient means for intelligent action Connectionism: a connectionist network has the necessary and sufficient means for intelligent action Activation Functions Representations Representations in a neural network need not be located in distinct physical locations The network’s “knowledge” lies in its pattern of weights and thresholds The power of distributed (as opposed to localist) networks comes from the fact that the network doesn’t need a separate unit to code every feature to which it is sensitive  In what sense do neural networks actually contain representations? Superpositional storage Once a network has been trained, all its knowledge is encoded in a single set of weights Each instance of information-processing involves an input vector and the weight vector This makes it difficult to think about the network’s knowledge as composed of discrete items (e.g. particular beliefs) Connectionist networks vs Physical symbol systems Physical Symbol systems: Connectionist networks: Discrete representations Representations often throughout missing or distributed Strokes in a Turing machine, Some distributed across Os and 1s in a digital nodes, hidden nodes often computer, Formulae in don’t represent anything Language of thought Lack of task specific rules Task specific rules Just domain general Machine table for Turing activation functions and machine, If … then rules in learning algorithms program for digital computers