Trusting SVM for piecewise linear CNNs

We present a novel layerwise optimization algorithm for the learning objective of Piecewise-Linear Convolutional Neural Networks (PL-CNNs), a large class of convolutional neural networks. Specifically, PL-CNNs employ piecewise linear non-linearities such as the commonly used ReLU and max-pool, and a...

詳細記述

書誌詳細
主要な著者: Berrada, L, Zisserman, A, Kumar, MP
フォーマット: Conference item
言語:English
出版事項: Curran Associates 2017