English
Related papers

Related papers: The Shattered Gradients Problem: If resnets are th…

200 papers

Deep ConvNets suffer from gradient signal degradation as network depth increases, limiting effective feature learning in complex architectures. ResNet addressed this through residual connections, but these fixed short-circuits cannot adapt…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Soudeep Ghoshal , Himanshu Buckchash

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

Deep learning requires several design choices, such as the nodes' activation functions and the widths, types, and arrangements of the layers. One consideration when making these choices is the vanishing-gradient problem, which is the…

Machine Learning · Computer Science 2021-06-07 Leni Ven , Johannes Lederer

As neural networks grow deeper and wider, learning networks with hard-threshold activations is becoming increasingly important, both for network quantization, which can drastically reduce time and energy requirements, and for creating large…

Machine Learning · Computer Science 2018-04-18 Abram L. Friesen , Pedro Domingos

Residual networks (Resnets) have become a prominent architecture in deep learning. However, a comprehensive understanding of Resnets is still a topic of ongoing research. A recent view argues that Resnets perform iterative refinement of…

Computer Vision and Pattern Recognition · Computer Science 2018-03-09 Stanisław Jastrzębski , Devansh Arpit , Nicolas Ballas , Vikas Verma , Tong Che , Yoshua Bengio

An open question in the Deep Learning community is why neural networks trained with Gradient Descent generalize well on real datasets even though they are capable of fitting random data. We propose an approach to answering this question…

Machine Learning · Computer Science 2020-02-26 Satrajit Chatterjee

Normalization layers are a staple in state-of-the-art deep neural network architectures. They are widely believed to stabilize training, enable higher learning rate, accelerate convergence and improve generalization, though the reason for…

Machine Learning · Computer Science 2019-03-13 Hongyi Zhang , Yann N. Dauphin , Tengyu Ma

The question of how and why the phenomenon of mode connectivity occurs in training deep neural networks has gained remarkable attention in the research community. From a theoretical perspective, two possible explanations have been proposed:…

Machine Learning · Computer Science 2021-10-22 Quynh Nguyen , Pierre Brechet , Marco Mondelli

Deep ResNets are recognized for achieving state-of-the-art results in complex machine learning tasks. However, the remarkable performance of these architectures relies on a training procedure that needs to be carefully crafted to avoid…

Machine Learning · Computer Science 2025-03-04 Pierre Marion , Adeline Fermanian , Gérard Biau , Jean-Philippe Vert

Permutation invariant neural networks are a promising tool for making predictions from sets. However, we show that existing permutation invariant architectures, Deep Sets and Set Transformer, can suffer from vanishing or exploding gradients…

Machine Learning · Computer Science 2022-07-15 Lily H. Zhang , Veronica Tozzo , John M. Higgins , Rajesh Ranganath

This paper revisits the so-called vanishing gradient phenomenon, which commonly occurs in deep randomly initialized neural networks. Leveraging an in-depth analysis of neural chains, we first show that vanishing gradients cannot be…

Machine Learning · Computer Science 2021-06-08 Antonio Orvieto , Jonas Kohler , Dario Pavllo , Thomas Hofmann , Aurelien Lucchi

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

Neural and Evolutionary Computing · Computer Science 2022-02-18 Yifan Hu , Yujie Wu , Lei Deng , Guoqi Li

Despite their massive success, training successful deep neural networks still largely relies on experimentally choosing an architecture, hyper-parameters, initialization, and training mechanism. In this work, we focus on determining the…

Machine Learning · Computer Science 2021-11-29 Umangi Jain , Harish G. Ramaswamy

Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing. Here we study their properties through their Gaussian Process and Neural Tangent kernels. We derive…

Machine Learning · Computer Science 2023-03-02 Daniel Barzilai , Amnon Geifman , Meirav Galun , Ronen Basri

We conduct mathematical analysis on the effect of batch normalization (BN) on gradient backpropogation in residual network training, which is believed to play a critical role in addressing the gradient vanishing/explosion problem, in this…

Machine Learning · Computer Science 2018-12-04 Abhishek Panigrahi , Yueru Chen , C. -C. Jay Kuo

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

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity patterns, e.g., various types of skip connections. Those…

Machine Learning · Computer Science 2022-10-13 Wuyang Chen , Wei Huang , Xinyu Gong , Boris Hanin , Zhangyang Wang

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. However, the supervised training of SNNs remains a hard problem due to the discontinuity of the spiking neuron…

Neural and Evolutionary Computing · Computer Science 2021-12-20 Mingqing Xiao , Qingyan Meng , Zongpeng Zhang , Yisen Wang , Zhouchen Lin

Deep learning has made significant progress in computer vision, specifically in image classification, object detection, and semantic segmentation. The skip connection has played an essential role in the architecture of deep neural…

Image and Video Processing · Electrical Eng. & Systems 2025-08-11 Guoping Xu , Xiaxia Wang , Xinglong Wu , Xuesong Leng , Yongchao Xu