Analysis of function of rectified linear unit used in deep learning

By K. Hara, Daisuke Saitoh, Hayaru Shouno. IEEE International Joint Conference on Neural Network, 2015

377 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/6a61b4967c161347525abc3ab5dba590c0cd99ca

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. Lahiru Jayasinghe
2. Chau Yuen
3. Shuihua Wang

In Computer Vision and Pattern Recognition

1. Lahiru Jayasinghe
2. Chau Yuen

In Signal Processing

1. Chau Yuen
2. Preetha Phillips
3. Shuihua Wang

Citations in the corpus

• RF-based Direction Finding of UAVs Using DNN (2017, background): “A single switching cycle is equivalent to N activations, starting from the first antenna to the N − th antenna.”
• Classification of Alzheimer’s Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling (2018, background): “To solve this problem, the rectified linear unit (ReLU) became popular [31], since it accelerated the convergence of stochastic gradient descent compared to the sigmoid function.”