Connectionism Flashcards
autoassociator
aim to prodcue the same output as learned even if input is noisy/degraded, learning occurs often by the Delta Rule
activiation function
depends on relation between net input and activity level which it produces, can be linear, threhold liners, binary or simoid
BCIs
using a neural interface system, machine translates neuronal activoty into control signals for assisitive devices
Backpropagation
calculates the error between desired level of activation and actual level, error send back to input units, changing weights -> supervised learning
Competitive learning
output units compete with each other to determine who has the largest response to a presented unit, 3 phases -> hippocampus
connectionism
using artificial neural networks