Deep learning

Pattern recognition (psychology)

Overfitting

Mathematics

Contextual image classification

Operating system

Image (mathematics)

Parametric statistics

Statistics

Initialization

Machine learning

Recurrent neural network

Types of artificial neural networks

Artificial intelligence

Programming language

Computer science

Scratch

Deep neural networks

Rectifier (neural networks)

Artificial neural network

Convolutional neural network

Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier neural networks for image classification from two aspects. First, we propose a Parametric Rectified Linear Unit (PReLU) that generalizes the traditional rectified unit. PReLU improves model fitting with nearly zero extra computational cost and little overfitting risk. Second, we derive a robust initialization method that particularly considers the rectifier nonlinearities. This method enables us to train extremely deep rectified models directly from scratch and to investigate deeper or wider network architectures. Based on the learnable activation and advanced initialization, we achieve 4.94% top-5 test error on the ImageNet 2012 classification dataset. This is a 26% relative improvement over the ILSVRC 2014 winner (GoogLeNet, 6.66% [33]). To our knowledge, our result is the first to surpass the reported human-level performance (5.1%, [26]) on this dataset.

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification