English
Related papers

Related papers: Speed Limits for Deep Learning

200 papers

The Bremermann-Bekenstein bound is a fundamental bound on the maximal rate with which information can be transmitted. However, its derivation relies on rather weak estimates and plausibility arguments, which make the application of the…

Quantum Physics · Physics 2017-06-14 Thiago V. Acconcia , Sebastian Deffner

We propose to optimize neural networks with a uniformly-distributed random learning rate. The associated stochastic gradient descent algorithm can be approximated by continuous stochastic equations and analyzed within the Fokker-Planck…

Machine Learning · Computer Science 2020-10-13 Daniele Musso

Spiking neural networks (SNNs) that enables energy efficient implementation on emerging neuromorphic hardware are gaining more attention. Yet now, SNNs have not shown competitive performance compared with artificial neural networks (ANNs),…

Neural and Evolutionary Computing · Computer Science 2018-11-26 Yujie Wu , Lei Deng , Guoqi Li , Jun Zhu , Luping Shi

Spiking Neural Networks (SNNs) are emerging as a brain-inspired alternative to traditional Artificial Neural Networks (ANNs), prized for their potential energy efficiency on neuromorphic hardware. Despite this, SNNs often suffer from…

Machine Learning · Computer Science 2025-05-29 Chengting Yu , Xiaochen Zhao , Lei Liu , Shu Yang , Gaoang Wang , Erping Li , Aili Wang

We analyze the learning dynamics of infinitely wide neural networks with a finite sized bottle-neck. Unlike the neural tangent kernel limit, a bottleneck in an otherwise infinite width network al-lows data dependent feature learning in its…

Machine Learning · Computer Science 2021-07-05 Etai Littwin , Omid Saremi , Shuangfei Zhai , Vimal Thilak , Hanlin Goh , Joshua M. Susskind , Greg Yang

Regularization in modern machine learning is crucial, and it can take various forms in algorithmic design: training set, model family, error function, regularization terms, and optimizations. In particular, the learning rate, which can be…

Machine Learning · Computer Science 2023-12-04 Yefan Zhou , Tianyu Pang , Keqin Liu , Charles H. Martin , Michael W. Mahoney , Yaoqing Yang

Multi-layer feedforward networks have been used to approximate a wide range of nonlinear functions. An important and fundamental problem is to understand the learnability of a network model through its statistical risk, or the expected…

Machine Learning · Computer Science 2022-06-28 Gen Li , Jie Ding

We discuss how various models of scale-free complex networks approach their limiting properties when the size N of the network grows. We focus mainly on equilibrated networks and their finite-size degree distributions. Our results show that…

Statistical Mechanics · Physics 2009-11-13 B. Waclaw , L. Bogacz , W. Janke

This paper proposes a framework for distributed, in-storage training of neural networks on clusters of computational storage devices. Such devices not only contain hardware accelerators but also eliminate data movement between the host and…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-10-14 Ali HeydariGorji , Mahdi Torabzadehkashi , Siavash Rezaei , Hossein Bobarshad , Vladimir Alves , Pai H. Chou

Recently, neural networks utilizing periodic activation functions have been proven to demonstrate superior performance in vision tasks compared to traditional ReLU-activated networks. However, there is still a limited understanding of the…

Machine Learning · Computer Science 2024-02-08 Hemanth Saratchandran , Shin-Fang Chng , Simon Lucey

Training Convolutional Neural Networks (CNNs) usually requires a large number of computational resources. In this paper, \textit{SparseTrain} is proposed to accelerate CNN training by fully exploiting the sparsity. It mainly involves three…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Pengcheng Dai , Jianlei Yang , Xucheng Ye , Xingzhou Cheng , Junyu Luo , Linghao Song , Yiran Chen , Weisheng Zhao

We investigate the mathematical foundations of neural networks in the infinite-width regime through the Neural Tangent Kernel (NTK). We propose the NTK-Eigenvalue-Controlled Residual Network (NTK-ECRN), an architecture integrating Fourier…

Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-11-24 Sian Jin , Guanpeng Li , Shuaiwen Leon Song , Dingwen Tao

Deep spiking neural networks (SNNs) are promising neural networks for their model capacity from deep neural network architecture and energy efficiency from SNNs' operations. To train deep SNNs, recently, spatio-temporal backpropagation…

Neural and Evolutionary Computing · Computer Science 2023-08-02 Seongsik Park , Jeonghee Jo , Jongkil Park , Yeonjoo Jeong , Jaewook Kim , Suyoun Lee , Joon Young Kwak , Inho Kim , Jong-Keuk Park , Kyeong Seok Lee , Gye Weon Hwang , Hyun Jae Jang

Despite recent progress in training spiking neural networks (SNNs) for classification, their application to continuous motor control remains limited. Here, we demonstrate that fully spiking architectures can be trained end-to-end to control…

Robotics · Computer Science 2026-02-04 Justus Huebotter , Pablo Lanillos , Marcel van Gerven , Serge Thill

Physics-informed neural networks (PINNs) numerically approximate the solution of a partial differential equation (PDE) by incorporating the residual of the PDE along with its initial/boundary conditions into the loss function. In spite of…

Computational Physics · Physics 2022-11-22 M. H. Saadat , B. Gjorgiev , L. Das , G. Sansavini

In recent years, the state-of-the-art in deep learning has been dominated by very large models that have been pre-trained on vast amounts of data. The paradigm is very simple: investing more computational resources (optimally) leads to…

Machine Learning · Computer Science 2024-05-24 Sotiris Anagnostidis , Gregor Bachmann , Imanol Schlag , Thomas Hofmann

In this work, a novel and model-based artificial neural network (ANN) training method is developed supported by optimal control theory. The method augments training labels in order to robustly guarantee training loss convergence and improve…

Optimization and Control · Mathematics 2023-03-17 Viktor Andersson , Balázs Varga , Vincent Szolnoky , Andreas Syrén , Rebecka Jörnsten , Balázs Kulcsár

The Neural Tangent Kernel (NTK) is the wide-network limit of a kernel defined using neural networks at initialization, whose embedding is the gradient of the output of the network with respect to its parameters. We study the "after kernel",…

Machine Learning · Computer Science 2021-12-14 Philip M. Long

Deep neural networks have recently achieved state of the art performance thanks to new training algorithms for rapid parameter estimation and new regularization methods to reduce overfitting. However, in practice the network architecture…

Machine Learning · Computer Science 2016-03-04 Minyoung Kim , Luca Rigazio