English
Related papers

Related papers: Learning Activation Functions: A new paradigm for …

200 papers

Activation functions (AFs) play a pivotal role in the performance of neural networks. The Rectified Linear Unit (ReLU) is currently the most commonly used AF. Several replacements to ReLU have been suggested but improvements have proven…

Neural and Evolutionary Computing · Computer Science 2022-06-27 Raz Lapid , Moshe Sipper

We present a Statistical Mechanics (SM) model of deep neural networks, connecting the energy-based and the feed forward networks (FFN) approach. We infer that FFN can be understood as performing three basic steps: encoding, representation…

Machine Learning · Computer Science 2019-06-07 Mirco Milletarí , Thiparat Chotibut , Paolo E. Trevisanutto

Deep Learning has revolutionized vision via convolutional neural networks (CNNs) and natural language processing via recurrent neural networks (RNNs). However, success stories of Deep Learning with standard feed-forward neural networks…

Machine Learning · Computer Science 2018-01-31 Günter Klambauer , Thomas Unterthiner , Andreas Mayr , Sepp Hochreiter

Deep Neural Networks (DNNs) are the current state-of-the-art models in many speech related tasks. There is a growing interest, though, for more biologically realistic, hardware friendly and energy efficient models, named Spiking Neural…

Machine Learning · Computer Science 2020-11-16 Thomas Pellegrini , Romain Zimmer , Timothée Masquelier

We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not. Interestingly, we find Swish, the recent popular NAS-searched activation, can be interpreted as a smooth approximation…

Computer Vision and Pattern Recognition · Computer Science 2021-04-19 Ningning Ma , Xiangyu Zhang , Ming Liu , Jian Sun

The paper briefy reviews several recent results on hierarchical architectures for learning from examples, that may formally explain the conditions under which Deep Convolutional Neural Networks perform much better in function approximation…

Machine Learning · Computer Science 2016-08-12 Hrushikesh Mhaskar , Tomaso Poggio

We analyze a simple one-hidden-layer neural network with ReLU activation functions and fixed biases, with one-dimensional input and output. We study both continuous and discrete versions of the model, and we rigorously prove the convergence…

Machine Learning · Computer Science 2026-04-10 Fabricio Macià , Shu Nakamura

The mathematical complexity and high dimensionality of neural networks slow both training and deployment, demanding heavy computational resources. This has driven the search for alternative architectures built from novel components,…

Applied Physics · Physics 2025-12-15 Jake McNaughton , A. H. Abbas , Ivan S. Maksymov

ReLU is widely seen as the default choice for activation functions in neural networks. However, there are cases where more complicated functions are required. In particular, recurrent neural networks (such as LSTMs) make extensive use of…

Machine Learning · Computer Science 2020-01-20 Nicholas Gerard Timmons , Andrew Rice

Neural networks are generally built by interleaving (adaptable) linear layers with (fixed) nonlinear activation functions. To increase their flexibility, several authors have proposed methods for adapting the activation functions…

Machine Learning · Statistics 2017-11-27 Simone Scardapane , Steven Van Vaerenbergh , Simone Totaro , Aurelio Uncini

Multi-task learning (MTL) is a common paradigm that seeks to improve the generalization performance of task learning by training related tasks simultaneously. However, it is still a challenging problem to search the flexible and accurate…

Machine Learning · Computer Science 2019-11-20 Yingru Liu , Xuewen Yang , Dongliang Xie , Xin Wang , Li Shen , Haozhi Huang , Niranjan Balasubramanian

Universal approximation theorem suggests that a shallow neural network can approximate any function. The input to neurons at each layer is a weighted sum of previous layer neurons and then an activation is applied. These activation…

Machine Learning · Computer Science 2020-10-30 Bhaavan Goel

Rectified linear activation units are important components for state-of-the-art deep convolutional networks. In this paper, we propose a novel S-shaped rectified linear activation unit (SReLU) to learn both convex and non-convex functions,…

Computer Vision and Pattern Recognition · Computer Science 2015-12-23 Xiaojie Jin , Chunyan Xu , Jiashi Feng , Yunchao Wei , Junjun Xiong , Shuicheng Yan

Researchers have proposed various activation functions. These activation functions help the deep network to learn non-linear behavior with a significant effect on training dynamics and task performance. The performance of these activations…

Computer Vision and Pattern Recognition · Computer Science 2020-01-07 Pravendra Singh , Munender Varshney , Vinay P. Namboodiri

Deep neural networks often suffer from poor performance or even training failure due to the ill-conditioned problem, the vanishing/exploding gradient problem, and the saddle point problem. In this paper, a novel method by acting the…

Computer Vision and Pattern Recognition · Computer Science 2021-07-12 Mei Liu , Liangming Chen , Xiaohao Du , Long Jin , Mingsheng Shang

It is fundamental to measure model complexity of deep neural networks. The existing literature on model complexity mainly focuses on neural networks with piecewise linear activation functions. Model complexity of neural networks with…

Machine Learning · Computer Science 2020-06-17 Xia Hu , Weiqing Liu , Jiang Bian , Jian Pei

Current research suggests that the key factors in designing neural network architectures involve choosing number of filters for every convolution layer, number of hidden neurons for every fully connected layer, dropout and pruning. The…

Machine Learning · Computer Science 2020-09-17 Himanshu Pradeep Aswani , Amit Sethi

Recent advancements in on-device training for deep neural networks have underscored the critical need for efficient activation compression to overcome the memory constraints of mobile and edge devices. As activations dominate memory usage…

Networking and Internet Architecture · Computer Science 2025-07-11 Renyuan Liu , Yuyang Leng , Kaiyan Liu , Shaohan Hu , Chun-Fu , Chen , Peijun Zhao , Heechul Yun , Shuochao Yao

It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly…

Machine Learning · Computer Science 2020-04-13 Abhishek Panigrahi , Abhishek Shetty , Navin Goyal

Residual networks have shown great success and become indispensable in recent deep neural network models. In this work, we aim to re-investigate the training process of residual networks from a novel social psychology perspective of…

Machine Learning · Computer Science 2023-05-05 Peng Ye , Tong He , Shengji Tang , Baopu Li , Tao Chen , Lei Bai , Wanli Ouyang
‹ Prev 1 3 4 5 6 7 10 Next ›