English
Related papers

Related papers: Deep Residual Networks and Weight Initialization

200 papers

Neural networks require careful weight initialization to prevent signals from exploding or vanishing. Existing initialization schemes solve this problem in specific cases by assuming that the network has a certain activation function or…

Machine Learning · Computer Science 2022-12-01 Garrett Bingham , Risto Miikkulainen

While training error of most deep neural networks degrades as the depth of the network increases, residual networks appear to be an exception. We show that the main reason for this is the Lyapunov stability of the gradient descent…

Machine Learning · Computer Science 2018-03-23 Kamil Nar , Shankar Sastry

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)…

Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks by end-to-end finetuning, which is highly memory-intensive for tasks with high-resolution data, e.g.,…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Chen Zhao , Shuming Liu , Karttikeya Mangalam , Guocheng Qian , Fatimah Zohra , Abdulmohsen Alghannam , Jitendra Malik , Bernard Ghanem

Training deep neural networks on large-scale datasets requires significant hardware resources whose costs (even on cloud platforms) put them out of reach of smaller organizations, groups, and individuals. Backpropagation, the workhorse for…

Machine Learning · Computer Science 2020-09-22 Alexander Ororbia , Ankur Mali , Daniel Kifer , C. Lee Giles

Recurrent Neural Networks (RNNs) produce state-of-art performance on many machine learning tasks but their demand on resources in terms of memory and computational power are often high. Therefore, there is a great interest in optimizing the…

Neural and Evolutionary Computing · Computer Science 2017-02-28 Joachim Ott , Zhouhan Lin , Ying Zhang , Shih-Chii Liu , Yoshua Bengio

We report, for the first time, on the cascade weight shedding phenomenon in deep neural networks where in response to pruning a small percentage of a network's weights, a large percentage of the remaining is shed over a few epochs during…

Machine Learning · Computer Science 2021-03-22 Kambiz Azarian , Fatih Porikli

We investigate the asymptotic properties of deep Residual networks (ResNets) as the number of layers increases. We first show the existence of scaling regimes for trained weights markedly different from those implicitly assumed in the…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , Renyuan Xu

Improving the resilience of a network is a fundamental problem in network science, which protects the underlying system from natural disasters and malicious attacks. This is traditionally achieved via successive degree-preserving edge…

Machine Learning · Computer Science 2022-05-24 Shanchao Yang , Kaili Ma , Baoxiang Wang , Tianshu Yu , Hongyuan Zha

The emergence of ResNet provides a powerful tool for training extremely deep networks. The core idea behind it is to change the learning goals of the network. It no longer learns new features from scratch but learns the difference between…

Computer Vision and Pattern Recognition · Computer Science 2025-06-03 Peng Hui , Jiamuyang Zhao , Changxin Li , Qingzhen Zhu

Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as…

Machine Learning · Computer Science 2015-06-16 Wenlin Chen , James T. Wilson , Stephen Tyree , Kilian Q. Weinberger , Yixin Chen

It is widely believed that the success of deep convolutional networks is based on progressively discarding uninformative variability about the input with respect to the problem at hand. This is supported empirically by the difficulty of…

Machine Learning · Computer Science 2018-06-25 Jörn-Henrik Jacobsen , Arnold Smeulders , Edouard Oyallon

Deep neural networks (DNNs) are typically optimized using various forms of mini-batch gradient descent algorithm. A major motivation for mini-batch gradient descent is that with a suitably chosen batch size, available computing resources…

Machine Learning · Computer Science 2022-10-25 Oyebade K. Oyedotun , Konstantinos Papadopoulos , Djamila Aouada

Neural networks have been able to achieve groundbreaking accuracy at tasks conventionally considered only doable by humans. Using stochastic gradient descent, optimization in many dimensions is made possible, albeit at a relatively high…

Machine Learning · Computer Science 2017-07-17 Hirsh R. Agarwal , Andrew Huang

In recent years, there has been increasing demand for automatic architecture search in deep learning. Numerous approaches have been proposed and led to state-of-the-art results in various applications, including image classification and…

Neural and Evolutionary Computing · Computer Science 2019-04-09 Zhiheng Huang , Bing Xiang

Residual networks (ResNets) employ skip connections in their networks -- reusing activations from previous layers -- to improve training convergence, but these skip connections create challenges for hardware implementations of ResNets. The…

Computer Vision and Pattern Recognition · Computer Science 2021-02-03 Olivia Weng , Alireza Khodamoradi , Ryan Kastner

Convolutional residual neural networks (ConvResNets), though overparameterized, can achieve remarkable prediction performance in practice, which cannot be well explained by conventional wisdom. To bridge this gap, we study the performance…

Machine Learning · Computer Science 2024-12-11 Zixuan Zhang , Kaiqi Zhang , Minshuo Chen , Yuma Takeda , Mengdi Wang , Tuo Zhao , Yu-Xiang Wang

Determining the optimal depth of a neural network is a fundamental yet challenging problem, typically resolved through resource-intensive experimentation. This paper introduces a formal theoretical framework to address this question by…

Machine Learning · Computer Science 2025-06-23 Qian Qi

Deep neural networks are powerful tools for solving nonlinear problems in science and engineering, but training highly accurate models becomes challenging as problem complexity increases. Non-convex optimization and sensitivity to…

Machine Learning · Computer Science 2026-04-20 Ethan Mulle , Wei Kang , Qi Gong

Residual neural networks are state-of-the-art deep learning models. Their continuous-depth analog, neural ordinary differential equations (ODEs), are also widely used. Despite their success, the link between the discrete and continuous…

Machine Learning · Statistics 2024-07-08 Pierre Marion , Yu-Han Wu , Michael E. Sander , Gérard Biau