English
Related papers

Related papers: The Backpropagation algorithm for a math student

200 papers

In this paper we investigate the supervised backpropagation training of multilayer neural networks from a dynamical systems point of view. We discuss some links with the qualitative theory of differential equations and introduce the overfly…

Machine Learning · Computer Science 2019-01-15 Alexei Tsygvintsev

We introduce a new second-order inertial optimization method for machine learning called INNA. It exploits the geometry of the loss function while only requiring stochastic approximations of the function values and the generalized…

Machine Learning · Computer Science 2021-08-17 Camille Castera , Jérôme Bolte , Cédric Févotte , Edouard Pauwels

A fundamental question in deep learning concerns the role played by individual layers in a deep neural network (DNN) and the transferable properties of the data representations which they learn. To the extent that layers have clear roles,…

Machine Learning · Computer Science 2019-06-14 Oded Ben-David , Zohar Ringel

The feed-forward architectures of recently proposed deep super-resolution networks learn representations of low-resolution inputs, and the non-linear mapping from those to high-resolution output. However, this approach does not fully…

Computer Vision and Pattern Recognition · Computer Science 2018-03-08 Muhammad Haris , Greg Shakhnarovich , Norimichi Ukita

Deep learning has revolutionized the computer vision and image classification domains. In this context Convolutional Neural Networks (CNNs) based architectures are the most widely applied models. In this article, we introduced two…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Seyedsaman Emami , Gonzalo Martínez-Muñoz

Binary Neural Networks (BNNs), which constrain both weights and activations to binary values, offer substantial reductions in computational complexity, memory footprint, and energy consumption. These advantages make them particularly well…

Machine Learning · Computer Science 2026-02-18 Luca Colombo , Fabrizio Pittorino , Daniele Zambon , Carlo Baldassi , Manuel Roveri , Cesare Alippi

In this paper, we construct approximated solutions of Differential Equations (DEs) using the Deep Neural Network (DNN). Furthermore, we present an architecture that includes the process of finding model parameters through experimental data,…

Numerical Analysis · Mathematics 2019-07-31 Hyeontae Jo , Hwijae Son , Hyung Ju Hwang , Eunheui Kim

In this paper, the problem of optimal gradient lossless compression in Deep Neural Network (DNN) training is considered. Gradient compression is relevant in many distributed DNN training scenarios, including the recently popular federated…

Machine Learning · Computer Science 2021-11-16 Zhong-Jing Chen , Eduin E. Hernandez , Yu-Chih Huang , Stefano Rini

A common practice in most of deep convolutional neural architectures is to employ fully-connected layers followed by Softmax activation to minimize cross-entropy loss for the sake of classification. Recent studies show that substitution or…

Machine Learning · Computer Science 2017-10-23 Arash Shahriari

In this work, we propose a novel backward differential deep learning-based algorithm for solving high-dimensional nonlinear backward stochastic differential equations (BSDEs), where the deep neural network (DNN) models are trained not only…

Numerical Analysis · Mathematics 2024-04-15 Lorenc Kapllani , Long Teng

Fractional-order differentiation has many characteristics different from integer-order differentiation. These characteristics can be applied to the optimization algorithms of artificial neural networks to obtain better results. However, due…

Machine Learning · Computer Science 2025-06-10 Xiaojun zhou , Chunna Zhao , Yaqun Huang , Chengli Zhou , Junjie Ye , Kemeng Xiang

Deep learning involves a difficult non-convex optimization problem, which is often solved by stochastic gradient (SG) methods. While SG is usually effective, it may not be robust in some situations. Recently, Newton methods have been…

Machine Learning · Statistics 2018-11-16 Chien-Chih Wang , Kent Loong Tan , Chih-Jen Lin

Stochastic gradient descent (SGD) has been the dominant optimization method for training deep neural networks due to its many desirable properties. One of the more remarkable and least understood quality of SGD is that it generalizes…

Machine Learning · Computer Science 2020-07-03 Erhan Bilal

The regularization and output consistency behavior of dropout and layer-wise pretraining for learning deep networks have been fairly well studied. However, our understanding of how the asymptotic convergence of backpropagation in deep…

Machine Learning · Computer Science 2017-02-23 Vamsi K Ithapu , Sathya N Ravi , Vikas Singh

Computing the loss gradient via backpropagation consumes considerable energy during deep learning (DL) model training. In this paper, we propose a novel approach to efficiently compute DL models' gradients to mitigate the substantial energy…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Challapalli Phanindra Revanth , Sumohana S. Channappayya , C Krishna Mohan

Deep neural networks (DNNs) have shown very promising results for various image restoration (IR) tasks. However, the design of network architectures remains a major challenging for achieving further improvements. While most existing…

Computer Vision and Pattern Recognition · Computer Science 2020-10-28 Weisheng Dong , Peiyao Wang , Wotao Yin , Guangming Shi , Fangfang Wu , Xiaotong Lu

This paper presents a concise mathematical framework for investigating both feed-forward and backward process, during the training to learn model weights, of an artificial neural network (ANN). Inspired from the idea of the two-step rule…

Neural and Evolutionary Computing · Computer Science 2023-05-02 Ahmed Boughammoura

Spiking neural networks (SNNs) are a viable alternative to conventional artificial neural networks when resource efficiency and computational complexity are of importance. A major advantage of SNNs is their binary information transfer…

Neural and Evolutionary Computing · Computer Science 2023-10-18 Daniel Gerlinghoff , Tao Luo , Rick Siow Mong Goh , Weng-Fai Wong

In this paper, we propose a learning rule based on a back-propagation (BP) algorithm that can be applied to a hardware-based deep neural network (HW-DNN) using electronic devices that exhibit discrete and limited conductance…

Neural and Evolutionary Computing · Computer Science 2018-08-02 Suhwan Lim , Jong-Ho Bae , Jai-Ho Eum , Sungtae Lee , Chul-Heung Kim , Dongseok Kwon , Byung-Gook Park , Jong-Ho Lee

We present Differentiable Neural Architectures (DNArch), a method that jointly learns the weights and the architecture of Convolutional Neural Networks (CNNs) by backpropagation. In particular, DNArch allows learning (i) the size of…

Machine Learning · Computer Science 2023-07-25 David W. Romero , Neil Zeghidour