Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Transactions on Signal Processing"
DOI: 10.1109/tsp.2020.2993153
Abstract: We study model recovery for data classification, where the training labels are generated from a one-hidden-layer neural network with sigmoid activations, also known as a single-layer feedforward network, and the goal is to recover the… read more here.
Keywords: layer neural; hidden layer; layer; cross entropy ... See more keywords