English
Related papers

Related papers: Dynamical Isometry for Residual Networks

200 papers

The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this…

Machine Learning · Computer Science 2024-01-18 Jianing Li , Vardan Papyan

Residual connections remain ubiquitous in modern neural network architectures nearly a decade after their introduction. Their widespread adoption is often credited to their dramatically improved trainability: residual networks train faster,…

Machine Learning · Computer Science 2025-06-18 Christian H. X. Ali Mehmeti-Göpel , Michael Wand

We present a new multilevel minimization framework for the training of deep residual networks (ResNets), which has the potential to significantly reduce training time and effort. Our framework is based on the dynamical system's viewpoint,…

Machine Learning · Computer Science 2020-04-15 Lisa Gaedke-Merzhäuser , Alena Kopaničáková , Rolf Krause

Deep neural networks (DNNs) have significantly advanced machine learning, with model depth playing a central role in their successes. The dynamical system modeling approach has recently emerged as a powerful framework, offering new…

Machine Learning · Computer Science 2026-02-25 Jinshu Huang , Mingfei Sun , Chunlin Wu

Learned inverse problem solvers exhibit remarkable performance in applications like image reconstruction tasks. These data-driven reconstruction methods often follow a two-step scheme. First, one trains the often neural network-based…

Recurrent Neural Networks (RNNs), more specifically their Long Short-Term Memory (LSTM) variants, have been widely used as a deep learning tool for tackling sequence-based learning tasks in text and speech. Training of such LSTM…

Machine Learning · Computer Science 2021-06-24 Anup Sarma , Sonali Singh , Huaipan Jiang , Rui Zhang , Mahmut T Kandemir , Chita R Das

Modern neural networks (NN) featuring a large number of layers (depth) and units per layer (width) have achieved a remarkable performance across many domains. While there exists a vast literature on the interplay between infinitely wide NNs…

Machine Learning · Statistics 2021-09-21 Stefano Peluchetti , Stefano Favaro

We analyze the input-output behavior of residual networks from a dynamical system point of view by disentangling the residual dynamics from the output activities before the classification stage. For a network with simple skip connections…

Computer Vision and Pattern Recognition · Computer Science 2021-05-12 Fereshteh Lagzi

Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful full-precision training and binary training. We bring some insights about why this…

Machine Learning · Computer Science 2020-04-22 Xinlin Li , Vahid Partovi Nia

In this paper, we study the trainability of rectified linear unit (ReLU) networks. A ReLU neuron is said to be dead if it only outputs a constant for any input. Two death states of neurons are introduced; tentative and permanent death. A…

Machine Learning · Computer Science 2020-10-23 Yeonjong Shin , George Em Karniadakis

An emerging design principle in deep learning is that each layer of a deep artificial neural network should be able to easily express the identity transformation. This idea not only motivated various normalization techniques, such as…

Machine Learning · Computer Science 2018-07-23 Moritz Hardt , Tengyu Ma

Despite the rapid progress of neuromorphic computing, inadequate capacity and insufficient representation power of spiking neural networks (SNNs) severely restrict their application scope in practice. Residual learning and shortcuts have…

Neural and Evolutionary Computing · Computer Science 2023-03-13 Yifan Hu , Lei Deng , Yujie Wu , Man Yao , Guoqi Li

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

A residual-networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This paper proposes a novel…

Computer Vision and Pattern Recognition · Computer Science 2017-03-07 Ke Zhang , Miao Sun , Tony X. Han , Xingfang Yuan , Liru Guo , Tao Liu

In this article, we take one step toward understanding the learning behavior of deep residual networks, and supporting the observation that deep residual networks behave like ensembles. We propose a new convolutional neural network…

Computer Vision and Pattern Recognition · Computer Science 2024-10-30 Masoud Abdi , Saeid Nahavandi

We study randomly initialized residual networks using mean field theory and the theory of difference equations. Classical feedforward neural networks, such as those with tanh activations, exhibit exponential behavior on the average when…

Neural and Evolutionary Computing · Computer Science 2017-12-27 Greg Yang , Samuel S. Schoenholz

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower than dense training,…

Machine Learning · Computer Science 2026-05-28 Mohammed Adnan , Rohan Jain , Tom Jacobs , Ekansh Sharma , Rahul G. Krishnan , Rebekka Burkholz , Yani Ioannou

Stable and efficient training of ReLU networks with large depth is highly sensitive to weight initialization. Improper initialization can cause permanent neuron inactivation dying ReLU and exacerbate gradient instability as network depth…

Machine Learning · Computer Science 2025-09-03 Hyungu Lee , Taehyeong Kim , Hayoung Choi

Weight initialization is important for faster convergence and stability of deep neural networks training. In this paper, a robust initialization method is developed to address the training instability in long short-term memory (LSTM)…

Invertible Rescaling Networks (IRNs) and their variants have witnessed remarkable achievements in various image processing tasks like image rescaling. However, we observe that IRNs with deeper networks are difficult to train, thus hindering…

Computer Vision and Pattern Recognition · Computer Science 2024-05-14 Jinmin Li , Tao Dai , Yaohua Zha , Yilu Luo , Longfei Lu , Bin Chen , Zhi Wang , Shu-Tao Xia , Jingyun Zhang