English
Related papers

Related papers: Volume-preserving Neural Networks

200 papers

Deep ResNet architectures have achieved state of the art performance on many tasks. While they solve the problem of gradient vanishing, they might suffer from gradient exploding as the depth becomes large (Yang et al. 2017). Moreover,…

Machine Learning · Computer Science 2021-03-19 Soufiane Hayou , Eugenio Clerico , Bobby He , George Deligiannidis , Arnaud Doucet , Judith Rousseau

Following the recent work on capacity allocation, we formulate the conjecture that the shattering problem in deep neural networks can only be avoided if the capacity propagation through layers has a non-degenerate continuous limit when the…

Machine Learning · Computer Science 2019-03-28 Jonathan Donier

After training complex deep learning models, a common task is to compress the model to reduce compute and storage demands. When compressing, it is desirable to preserve the original model's per-example decisions (e.g., to go beyond top-1…

Machine Learning · Computer Science 2022-10-18 Jerry Chee , Megan Renz , Anil Damle , Christopher De Sa

The vanishing and exploding gradient problems are well-studied obstacles that make it difficult for recurrent neural networks to learn long-term time dependencies. We propose a reparameterization of standard recurrent neural networks to…

Machine Learning · Computer Science 2016-12-14 Victor Dorobantu , Per Andre Stromhaug , Jess Renteria

Rectified Linear Units (ReLU) have become the main model for the neural units in current deep learning systems. This choice has been originally suggested as a way to compensate for the so called vanishing gradient problem which can undercut…

Disordered Systems and Neural Networks · Physics 2024-05-06 Carlo Baldassi , Enrico M. Malatesta , Riccardo Zecchina

We study deep neural networks with polynomial activations, particularly their expressive power. For a fixed architecture and activation degree, a polynomial neural network defines an algebraic map from weights to polynomials. The image of…

Machine Learning · Computer Science 2019-05-30 Joe Kileel , Matthew Trager , Joan Bruna

Vanishing and exploding gradients are two of the main obstacles in training deep neural networks, especially in capturing long range dependencies in recurrent neural networks~(RNNs). In this paper, we present an efficient parametrization of…

Machine Learning · Computer Science 2018-03-28 Jiong Zhang , Qi Lei , Inderjit S. Dhillon

This paper presents a transformative framework for artificial neural networks over graded vector spaces, tailored to model hierarchical and structured data in fields like algebraic geometry and physics. By exploiting the algebraic…

Artificial Intelligence · Computer Science 2026-01-07 Tony Shaska

Deep feedforward and recurrent networks have achieved impressive results in many perception and language processing applications. This success is partially attributed to architectural innovations such as convolutional and long short-term…

Machine Learning · Statistics 2015-11-24 Arvind Neelakantan , Luke Vilnis , Quoc V. Le , Ilya Sutskever , Lukasz Kaiser , Karol Kurach , James Martens

Gradient-based neural network training traditionally enforces symmetry between forward and backward propagation, requiring activation functions to be differentiable (or sub-differentiable) and strictly monotonic in certain regions to…

Neural and Evolutionary Computing · Computer Science 2025-09-10 Luigi Troiano , Francesco Gissi , Vincenzo Benedetto , Genny Tortora

Capsule Networks outperform Convolutional Neural Networks in learning the part-whole relationships with viewpoint invariance, and the credit goes to their multidimensional capsules. It was assumed that increasing the number of capsule…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Siddharth Sahu , Abdulrahman Altahhan

Deep neural networks are known to suffer from exploding or vanishing gradients as depth increases, a phenomenon closely tied to the spectral behavior of the input-output Jacobian. Prior work has identified critical initialization schemes…

Machine Learning · Computer Science 2025-11-25 Benjamin Dadoun , Soufiane Hayou , Hanan Salam , Mohamed El Amine Seddik , Pierre Youssef

In this paper, we develop a new optimization framework for the least squares learning problem via fully connected neural networks or physics-informed neural networks. The gradient descent sometimes behaves inefficiently in deep learning…

Machine Learning · Computer Science 2025-05-01 Yaru Liu , Yiqi Gu , Michael K. Ng

Recent works show that reducing the number of layers in a convolutional neural network can enhance efficiency while maintaining the performance of the network. Existing depth compression methods remove redundant non-linear activation…

Machine Learning · Computer Science 2024-07-09 Jinuk Kim , Marwa El Halabi , Mingi Ji , Hyun Oh Song

Deep neural networks can suffer from the exploding and vanishing activation problem, in which the networks fail to train properly because the neural signals either amplify or attenuate across the layers and become saturated. While other…

Machine Learning · Computer Science 2021-08-24 Hao-Yuan Chang , Kang L. Wang

The exploding and vanishing gradient problem has been the major conceptual principle behind most architecture and training improvements in recurrent neural networks (RNNs) during the last decade. In this paper, we argue that this principle,…

Machine Learning · Computer Science 2020-03-06 Antônio H. Ribeiro , Koen Tiels , Luis A. Aguirre , Thomas B. Schön

A Deep Neural Network (DNN) is a composite function of vector-valued functions, and in order to train a DNN, it is necessary to calculate the gradient of the loss function with respect to all parameters. This calculation can be a…

Machine Learning · Computer Science 2023-06-02 Saeed Damadi , Golnaz Moharrer , Mostafa Cham

We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient descent can achieve optimality \emph{without} massive…

Machine Learning · Computer Science 2024-10-11 Semih Cayci , Atilla Eryilmaz

Recent theoretical work has demonstrated that deep neural networks have superior performance over shallow networks, but their training is more difficult, e.g., they suffer from the vanishing gradient problem. This problem can be typically…

Machine Learning · Statistics 2021-11-03 Lu Lu , Yanhui Su , George Em Karniadakis

Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-18 Shixiang Tang , Dapeng Chen , Jinguo Zhu , Shijie Yu , Wanli Ouyang