Size and Depth Separation in Approximating Benign Functions with Neural Networks.

Gal Vardi Daniel Reichman Toniann Pitassi Ohad Shamir

Published in: COLT (2021)

Keyphrases

neural network
pattern recognition
artificial neural networks
small size
computational complexity
genetic algorithm
sufficient conditions
feed forward
recurrent neural networks
linear functions
machine learning
bayesian networks
fuzzy logic
back propagation
memory requirements
maximum number