English
Related papers

Related papers: Backpropagation in matrix notation

200 papers

Back-propagation has been the workhorse of recent successes of deep learning but it relies on infinitesimal effects (partial derivatives) in order to perform credit assignment. This could become a serious issue as one considers deeper and…

Machine Learning · Computer Science 2015-11-26 Dong-Hyun Lee , Saizheng Zhang , Asja Fischer , Yoshua Bengio

Backpropagation's main limitation is its need to store intermediate activations (residuals) during the forward pass, which restricts the depth of trainable networks. This raises a fundamental question: can we avoid storing these…

Machine Learning · Computer Science 2026-05-25 Dmitrii Krylov , Armin Karamzade , Roy Fox

We describe recurrent neural networks (RNNs), which have attracted great attention on sequential tasks, such as handwriting recognition, speech recognition and image to text. However, compared to general feedforward neural networks, RNNs…

Machine Learning · Computer Science 2018-01-16 Gang Chen

We present a linear algebra formulation of backpropagation which allows the calculation of gradients by using a generically written ``backslash'' or Gaussian elimination on triangular systems of equations. Generally, the matrix elements are…

Numerical Analysis · Mathematics 2023-09-01 Alan Edelman , Ekin Akyurek , Yuyang Wang

A multimodal network encodes relationships between the same set of nodes in multiple settings, and network alignment is a powerful tool for transferring information and insight between a pair of networks. We propose a method for multimodal…

Social and Information Networks · Computer Science 2017-03-31 Huda Nassar , David F. Gleich

In this paper, we introduce directed networks called `divergence network' in order to perform graphical calculation of divergence functions. By using the divergence networks, we can easily understand the geometric meaning of calculation…

Machine Learning · Computer Science 2018-11-02 Tomohiro Nishiyama

Given a differentiable network architecture and loss function, we revisit optimizing the network's neurons in function space using Boosted Backpropagation (Grubb & Bagnell, 2010), in contrast to optimizing in parameter space. From this…

Machine Learning · Computer Science 2025-02-04 Daniel Munoz

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient…

Machine Learning · Computer Science 2023-06-13 Louis Fournier , Stéphane Rivaud , Eugene Belilovsky , Michael Eickenberg , Edouard Oyallon

We describe, implement and test a novel method for training neural networks to estimate the Jacobian matrix $J$ of an unknown multivariate function $F$. The training set is constructed from finitely many pairs $(x,F(x))$ and it contains no…

Machine Learning · Computer Science 2022-04-04 Frédéric Latrémolière , Sadananda Narayanappa , Petr Vojtěchovský

The de facto algorithm for training the back pass of a feedforward neural network is backpropagation (BP). The use of almost-everywhere differentiable activation functions made it efficient and effective to propagate the gradient backwards…

Neural and Evolutionary Computing · Computer Science 2022-06-14 John Waldo

We establish a convergence theorem for a certain type of stochastic gradient descent, which leads to a convergent variant of the back-propagation algorithm

Optimization and Control · Mathematics 2021-04-02 Hao Wu

Regressing rotations on SO(3) manifold using deep neural networks is an important yet unsolved problem. The gap between the Euclidean network output space and the non-Euclidean SO(3) manifold imposes a severe challenge for neural network…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Jiayi Chen , Yingda Yin , Tolga Birdal , Baoquan Chen , Leonidas Guibas , He Wang

In this paper we use deep feedforward artificial neural networks to approximate solutions to partial differential equations in complex geometries. We show how to modify the backpropagation algorithm to compute the partial derivatives of the…

Machine Learning · Statistics 2018-08-28 Jens Berg , Kaj Nyström

Deep neural network architectures have recently produced excellent results in a variety of areas in artificial intelligence and visual recognition, well surpassing traditional shallow architectures trained using hand-designed features. The…

Computer Vision and Pattern Recognition · Computer Science 2016-04-15 Catalin Ionescu , Orestis Vantzos , Cristian Sminchisescu

We present a derivation of the gradients of feedforward neural networks using Fr\'echet calculus which is arguably more compact than the ones usually presented in the literature. We first derive the gradients for ordinary neural networks…

Machine Learning · Computer Science 2022-09-28 Thomas Hamm

Stochastic gradient descent (SGD) has achieved great success in training deep neural network, where the gradient is computed through back-propagation. However, the back-propagated values of different layers vary dramatically. This…

Machine Learning · Statistics 2018-02-28 Huishuai Zhang , Wei Chen , Tie-Yan Liu

This paper studies interpretability of convolutional networks by means of saliency maps. Most approaches based on Class Activation Maps (CAM) combine information from fully connected layers and gradient through variants of backpropagation.…

Computer Vision and Pattern Recognition · Computer Science 2024-04-24 Felipe Torres Figueroa , Hanwei Zhang , Ronan Sicre , Yannis Avrithis , Stephane Ayache

In a variety of problems originating in supervised, unsupervised, and reinforcement learning, the loss function is defined by an expectation over a collection of random variables, which might be part of a probabilistic model or the external…

Machine Learning · Computer Science 2016-01-06 John Schulman , Nicolas Heess , Theophane Weber , Pieter Abbeel

Matrix factorization is an important mathematical problem encountered in the context of dictionary learning, recommendation systems and machine learning. We introduce a new `decimation' scheme that maps it to neural network models of…

Disordered Systems and Neural Networks · Physics 2023-07-12 Francesco Camilli , Marc Mézard

This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the…

Machine Learning · Statistics 2016-12-07 Tian Han , Yang Lu , Song-Chun Zhu , Ying Nian Wu