论文信息 - Piecewise Linear Multilayer Perceptrons and Dropout

Piecewise Linear Multilayer Perceptrons and Dropout

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.

Ian J. Goodfellow

[1] Nitish Srivastava,et al. Improving neural networks by preventing co-adaptation of feature detectors , 2012, ArXiv.

[2] Yoshua Bengio,et al. Deep Sparse Rectifier Neural Networks , 2011, AISTATS.