Piecewise Linear Multilayer Perceptrons and Dropout

By Ian J. Goodfellow. 2013

7 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Model Architectures

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Shuicheng Yan
2. Min Lin
3. Qiang Chen
4. Philip H. S. Torr
5. Yi Yang
6. Jiashi Feng
7. Dacheng Tao
8. Yunchao Wei

In Model Architectures

1. Shuicheng Yan
2. Qiang Chen
3. Min Lin
4. Kaiming He
5. Ross B. Girshick
6. Gao Huang
7. Aysegul Dundar
8. Max Welling

Citations in the corpus

• Network In Network (2013, background): “As in CNN, filters from higher layers map to larger regions in the original input.”