English
Related papers

Related papers: Norm-preserving Orthogonal Permutation Linear Unit…

200 papers

We introduce the "exponential linear unit" (ELU) which speeds up learning in deep neural networks and leads to higher classification accuracies. Like rectified linear units (ReLUs), leaky ReLUs (LReLUs) and parametrized ReLUs (PReLUs), ELUs…

Machine Learning · Computer Science 2016-02-23 Djork-Arné Clevert , Thomas Unterthiner , Sepp Hochreiter

In this work, we examine the approximation capabilities of deep neural networks utilizing the Rectified Quadratic Unit (ReQU) activation function, defined as \(\max(0,x)^2\), for approximating H\"older-regular functions with respect to the…

Machine Learning · Computer Science 2024-11-12 Ahmed Abdeljawad

In our previous work [Ma and Chan (2023)], we presented a feedforward unitary equivariant neural network. We proposed three distinct activation functions tailored for this network: a softsign function with a small residue, an identity…

Machine Learning · Computer Science 2024-11-25 Pui-Wai Ma

Large Language Models (LLMs) with billions of parameters have drastically transformed AI applications. However, their demanding computation during inference has raised significant challenges for deployment on resource-constrained devices.…

In this article we present new results on neural networks with linear threshold activation functions. We precisely characterize the class of functions that are representable by such neural networks and show that 2 hidden layers are…

Machine Learning · Computer Science 2023-10-20 Sammy Khalife , Hongyu Cheng , Amitabh Basu

In the era of Deep Neural Network based solutions for a variety of real-life tasks, having a compact and energy-efficient deployable model has become fairly important. Most of the existing deep architectures use Rectifier Linear Unit (ReLU)…

Machine Learning · Computer Science 2022-06-02 Nancy Nayak , Sheetal Kalyani

Recent seminal work at the intersection of deep neural networks practice and random matrix theory has linked the convergence speed and robustness of these networks with the combination of random weight initialization and nonlinear…

Machine Learning · Computer Science 2019-05-07 Pierre H. Richemond , Yike Guo

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

In recent years, neural networks have enjoyed a renaissance as function approximators in reinforcement learning. Two decades after Tesauro's TD-Gammon achieved near top-level human performance in backgammon, the deep reinforcement learning…

Machine Learning · Computer Science 2017-11-03 Stefan Elfwing , Eiji Uchibe , Kenji Doya

Optical neural networks usually execute the linear multiply-accumulate operation in the optical domain, whereas the nonlinear activation function is mostly implemented in the digital or electrical domain. Here we demonstrate a broadband…

Optics · Physics 2025-07-02 Hai-Fei Guo , Zheng-Can Sun , Yi-Wei Shen , Rui-Qian Li , Xing Li , Cheng Wang

Rectified Linear Units (ReLUs) have been shown to ameliorate the vanishing gradient problem, allow for efficient backpropagation, and empirically promote sparsity in the learned parameters. They have led to state-of-the-art results in a…

Machine Learning · Computer Science 2016-05-30 Xingyuan Pan , Vivek Srikumar

We propose a simple extension to the ReLU-family of activation functions that allows them to shift the mean activation across a layer towards zero. Combined with proper weight initialization, this alleviates the need for normalization…

Machine Learning · Statistics 2018-03-16 Lars Eidnes , Arild Nøkland

A general procedure for introducing parametric, learned, nonlinearity into activation functions is found to enhance the accuracy of representative neural networks without requiring significant additional computational resources. Examples…

Machine Learning · Computer Science 2025-05-14 David Yevick

This paper introduces scalable, sampling-based algorithms that optimize trained neural networks with ReLU activations. We first propose an iterative algorithm that takes advantage of the piecewise linear structure of ReLU neural networks…

Optimization and Control · Mathematics 2022-06-07 Georgia Perakis , Asterios Tsiourvas

In this work, we consider the approximation of a large class of bounded functions, with minimal regularity assumptions, by ReLU neural networks. We show that the approximation error can be bounded from above by a quantity proportional to…

Machine Learning · Statistics 2026-02-27 Owen Davis , Gianluca Geraci , Mohammad Motamed

Activation functions play a decisive role in determining the capacity of Deep Neural Networks as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions…

Computer Vision and Pattern Recognition · Computer Science 2023-05-31 Jamshaid Ul Rahman , Faiza Makhdoom , Dianchen Lu

We propose and analyze a new family of algorithms for training neural networks with ReLU activations. Our algorithms are based on the technique of alternating minimization: estimating the activation patterns of each ReLU for all given…

Machine Learning · Computer Science 2018-10-12 Gauri Jagatap , Chinmay Hegde

We introduce a variational framework to learn the activation functions of deep neural networks. Our aim is to increase the capacity of the network while controlling an upper-bound of the actual Lipschitz constant of the input-output…

Machine Learning · Computer Science 2023-07-19 Shayan Aziznejad , Harshit Gupta , Joaquim Campos , Michael Unser

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

We introduce stochastic activations. This novel strategy randomly selects between several non-linear functions in the feed-forward layer of a large language model. In particular, we choose between SILU or RELU depending on a Bernoulli draw.…

‹ Prev 1 4 5 6 7 8 10 Next ›