English
Related papers

Related papers: Learning Neural Networks with Sparse Activations

200 papers

Sparse neural networks have received increasing interest due to their small size compared to dense networks. Nevertheless, most existing works on neural network theory have focused on dense neural networks, and the understanding of sparse…

Machine Learning · Computer Science 2022-05-18 Dachao Lin , Ruoyu Sun , Zhihua Zhang

An extension to a recently introduced binary neural network is proposed in order to allow the learning of sparse messages, in large numbers and with high memory efficiency. This new network is justified both in biological and informational…

Neural and Evolutionary Computing · Computer Science 2012-08-21 Behrooz Kamary Aliabadi , Claude Berrou , Vincent Gripon , Xiaoran Jiang

Sparse neural networks are mainly motivated by ressource efficiency since they use fewer parameters than their dense counterparts but still reach comparable accuracies. This article empirically investigates whether sparsity could also…

Cryptography and Security · Computer Science 2024-05-27 Antoine Gonon , Léon Zheng , Clément Lalanne , Quoc-Tung Le , Guillaume Lauga , Can Pouliquen

We investigate filter level sparsity that emerges in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay.…

Machine Learning · Computer Science 2019-04-08 Dushyant Mehta , Kwang In Kim , Christian Theobalt

Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and usually require an…

Machine Learning · Computer Science 2018-06-05 Maohua Zhu , Jason Clemons , Jeff Pool , Minsoo Rhu , Stephen W. Keckler , Yuan Xie

In this paper, we propose a new scheme for modelling the diverse behavior of neurons. We introduce the conditional activation, in which a neurons activation function is dynamically modified by a control signal. We apply this method to…

Neural and Evolutionary Computing · Computer Science 2018-03-15 Albert Lee , Bonnie Lam , Wenyuan Li , Hochul Lee , Wei-Hao Chen , Meng-Fan Chang , Kang. -L. Wang

A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing…

Machine Learning · Computer Science 2022-06-23 Alex Bäuerle , Daniel Jönsson , Timo Ropinski

We introduce a dynamic sparse training algorithm based on linearized Bregman iterations / mirror descent that exploits the naturally incurred sparsity by alternating between periods of static and dynamic sparsity pattern updates. The key…

Machine Learning · Computer Science 2026-05-19 Yannick Lunk , Sebastian J. Scott , Leon Bungert

The scope of research in the domain of activation functions remains limited and centered around improving the ease of optimization or generalization quality of neural networks (NNs). However, to develop a deeper understanding of deep…

Machine Learning · Computer Science 2020-12-10 Mohit Goyal , Rajan Goyal , Brejesh Lall

Many transformations in deep learning architectures are sparsely connected. When such transformations cannot be designed by hand, they can be learned, even through plain backpropagation, for instance in attention mechanisms. However, during…

Machine Learning · Statistics 2018-10-23 Peter Bloem

Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse…

Neural and Evolutionary Computing · Computer Science 2019-06-28 Shiwei Liu , Decebal Constantin Mocanu , Mykola Pechenizkiy

Catastrophic forgetting remains a significant challenge to continual learning for decades. While recent works have proposed effective methods to mitigate this problem, they mainly focus on the algorithmic side. Meanwhile, we do not fully…

Machine Learning · Computer Science 2023-10-03 Qingfeng Lan , A. Rupam Mahmood

Conventional deep convolutional neural networks (CNNs) apply convolution operators uniformly in space across all feature maps for hundreds of layers - this incurs a high computational cost for real-time applications. For many problems such…

Computer Vision and Pattern Recognition · Computer Science 2018-06-08 Mengye Ren , Andrei Pokrovsky , Bin Yang , Raquel Urtasun

Large Language Models (LLMs) offer strong capabilities but incur high inference costs due to dense computation and memory access. Training-free activation sparsity is a promising approach for efficient LLM inference, yet existing methods…

Machine Learning · Computer Science 2026-02-17 Lei Chen , Yuan Meng , Xiaoyu Zhan , Zhi Wang , Wenwu Zhu

Deep neural networks have become very popular in modeling complex nonlinear processes due to their extraordinary ability to fit arbitrary nonlinear functions from data with minimal expert intervention. However, they are almost always…

Chemical Physics · Physics 2023-01-16 Erlend Torje Berg Lundby , Adil Rasheed , Ivar Johan Halvorsen , Jan Tommy Gravdahl

Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference. Dynamic sparse training (DST), as a leading sparse training approach, can…

Machine Learning · Computer Science 2023-11-13 Lu Yin , Gen Li , Meng Fang , Li Shen , Tianjin Huang , Zhangyang Wang , Vlado Menkovski , Xiaolong Ma , Mykola Pechenizkiy , Shiwei Liu

Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network…

Machine Learning · Computer Science 2019-07-17 Shuhao Xia , Yuanming Shi

Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to…

Machine Learning · Computer Science 2019-12-06 Justin Cosentino , Federico Zaiter , Dan Pei , Jun Zhu

Overfitting is one of the fundamental challenges when training convolutional neural networks and is usually identified by a diverging training and test loss. The underlying dynamics of how the flow of activations induce overfitting is…

Machine Learning · Computer Science 2021-04-14 Karim Huesmann , Luis Garcia Rodriguez , Lars Linsen , Benjamin Risse

Recent work has demonstrated the curse of depth in large language models (LLMs), where later layers contribute less to learning and representation than earlier layers. Such under-utilization is linked to the accumulated growth of variance…

Computation and Language · Computer Science 2026-03-17 Dilxat Muhtar , Xinyuan Song , Sebastian Pokutta , Max Zimmer , Nico Pelleriti , Thomas Hofmann , Shiwei Liu