NECVLGMLMar 22, 2018

Deep Learning using Rectified Linear Units (ReLU)

arXiv:1803.08375v2355 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental addition to studies exploring alternative classification functions for deep learning.

The paper tackles the problem of using rectified linear units (ReLU) as a classification function in deep neural networks instead of the conventional Softmax, and the result is a method that thresholds raw scores to provide class predictions via argmax.

We introduce the use of rectified linear units (ReLU) as the classification function in a deep neural network (DNN). Conventionally, ReLU is used as an activation function in DNNs, with Softmax function as their classification function. However, there have been several studies on using a classification function other than Softmax, and this study is an addition to those. We accomplish this by taking the activation of the penultimate layer $h_{n - 1}$ in a neural network, then multiply it by weight parameters $θ$ to get the raw scores $o_{i}$. Afterwards, we threshold the raw scores $o_{i}$ by $0$, i.e. $f(o) = \max(0, o_{i})$, where $f(o)$ is the ReLU function. We provide class predictions $\hat{y}$ through argmax function, i.e. argmax $f(x)$.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes