Work

Piecewise Linear Multilayer Perceptrons and Dropout

Year: 2013
Type: preprint
Abstract: We propose a new type of hidden layer for a multilayer perceptron, and demonstrate that it obtains the best reported performance for an MLP on the MNIST dataset.
Language: English
Open Access status: green
OpenAlex ID: W1908107260
Cites: 1
Cited by: 4
Related to: 10