paper-with-me

Papers

Empirical Evaluation of Rectified Activations in Convolutional Network

2015-05-05 · Bing Xu, Naiyan Wang, Tianqi Chen, Mu Li

In this paper we investigate the performance of different types of rectified activation functions in convolutional neural network: standard rectified linear unit (ReLU), leaky rectified linear unit (Leaky ReLU), parametric rectified linear unit (PReLU) and a new randomized leaky rectified linear units (RReLU). We evaluate these activation function on standard image classification task. Our experiments suggest that incorporating a non-zero slope for negative part in rectified activation units could consistently improve the results. Thus our findings are negative on the common belief that sparsity is the key of good performance in ReLU. Moreover, on small scale dataset, using deterministic negative slope or learning it are both prone to overfitting. They are not as effective as using their randomized counterpart. By using RReLU, we achieved 75.68\% accuracy on CIFAR-100 test set without multiple test or ensemble.

📄 PDF Abstract BibTeX arXiv:1505.00853

Code (2)

OsvaldN/APS360_Project pytorch
spinterRu/fashion_mnist tf

Tasks

General Classificationimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
RReLU Randomized Leaky Rectified Linear Units, or RReLU, are an activation function that randomly samples the negative slope for activation values. It was first proposed and…

Similar Papers 제목 키워드 기반

Structured Convolution Matrices for Energy-efficient Deep learning

2016-06-08 · Rathinakumar Appuswamy, Tapan Nayak, John Arthur, Steven Esser 외

We derive a relationship between network representation in energy-efficient neuromorphic architectures and block Toplitz convolutional matrices. Inspired by this connection, we develop deep convolutional networks using a…

Deep LearningGeneral Classification

Smooth activations and reproducibility in deep networks

2020-10-20 · Gil I. Shamir, Dong Lin, Lorenzo Coviello

Deep networks are gradually penetrating almost every domain in our lives due to their amazing success. However, with substantive performance accuracy improvements comes the price of \emph{irreproducibility}. Two identica…

Overcoming Overfitting and Large Weight Update Problem in Linear Rectifiers: Thresholded Exponential Rectified Linear Units

2020-06-04 · Vijay Pandey

In past few years, linear rectified unit activation functions have shown its significance in the neural networks, surpassing the performance of sigmoid activations. RELU (Nair & Hinton, 2010), ELU (Clevert et al., 2015),…

Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy Environments

2024-02-04 · Vivswan Shah, Nathan Youngblood

Real-world analog systems intrinsically suffer from noise that can impede model convergence and accuracy on a variety of deep learning models. We demonstrate that differentiable activations like GELU and SiLU enable robu…

Quantization

VRA: Variational Rectified Activation for Out-of-distribution Detection

2023-02-23 · NeurIPS 2023 11

Out-of-distribution (OOD) detection is critical to building reliable machine learning systems in the open world. Researchers have proposed various strategies to reduce model overconfidence on OOD data. Among them, ReAct …

Out-of-Distribution DetectionOut of Distribution (OOD) Detection