An adaptive network for encoding data using piecewise linear functions

摘要

An objective function that encourages an encoder to have the minimum overall Euclidean reconstruction error is shown to lead to encoders that can be implemented using functions that depend only in a piece-wise linear fashion on the input vector.From the neural network viewpoint, the optimal form of the probability that each neuron is the next one to fire is a piecewise linear function of the input vector.