English
Related papers

Related papers: Towards Understanding Neural Collapse: The Effects…

200 papers

Deep neural networks are widely used in various domains. However, the nature of computations at each layer of the deep networks is far from being well understood. Increasing the interpretability of deep neural networks is thus important.…

Machine Learning · Computer Science 2018-12-19 Haiping Huang

Memorization of training data is an active research area, yet our understanding of the inner workings of neural networks is still in its infancy. Recently, Haim et al. (2022) proposed a scheme to reconstruct training samples from multilayer…

Machine Learning · Computer Science 2023-11-06 Gon Buzaglo , Niv Haim , Gilad Yehudai , Gal Vardi , Yakir Oz , Yaniv Nikankin , Michal Irani

Batch normalization is widely used in deep learning to normalize intermediate activations. Deep networks suffer from notoriously increased training complexity, mandating careful initialization of weights, requiring lower learning rates,…

Machine Learning · Statistics 2022-10-19 Lakshmi Annamalai , Chetan Singh Thakur

The weights of neural networks (NNs) have recently gained prominence as a new data modality in machine learning, with applications ranging from accuracy and hyperparameter prediction to representation learning or weight generation. One…

Machine Learning · Computer Science 2025-03-24 Léo Meynent , Ivan Melev , Konstantin Schürholt , Göran Kauermann , Damian Borth

Large batch size training in deep neural networks (DNNs) possesses a well-known 'generalization gap' that remarkably induces generalization performance degradation. However, it remains unclear how varying batch size affects the structure of…

Machine Learning · Computer Science 2020-12-17 Fengli Gao , Huicai Zhong

We characterize the exact solutions to neural network descrambling--a mathematical model for explaining the fully connected layers of trained neural networks (NNs). By reformulating the problem to the minimization of the Brockett function…

Machine Learning · Computer Science 2024-09-04 Shashank Sule , Richard G. Spencer , Wojciech Czaja

We study how different output layer parameterizations of a deep neural network affects learning and forgetting in continual learning settings. The following three effects can cause catastrophic forgetting in the output layer: (1) weights…

Machine Learning · Computer Science 2022-08-19 Timothée Lesort , Thomas George , Irina Rish

Improving sparsity of deep neural networks (DNNs) is essential for network compression and has drawn much attention. In this work, we disclose a harmful sparsifying process called filter collapse, which is common in DNNs with batch…

Machine Learning · Computer Science 2020-02-03 Sheng Zhou , Xinjiang Wang , Ping Luo , Litong Feng , Wenjie Li , Wei Zhang

Developing strong AI signifies the arrival of technological singularity, contributing greatly to advancing human civilization and resolving social issues. Neural networks (NNs) and deep learning, which utilize NNs, are expected to lead to…

Machine Learning · Computer Science 2024-09-09 Kei Itoh

When finetuning a convolutional neural network (CNN) on data from a new domain, catastrophic forgetting will reduce performance on the original training data. Elastic Weight Consolidation (EWC) is a recent technique to prevent this, which…

Image and Video Processing · Electrical Eng. & Systems 2019-09-26 Karin van Garderen , Sebastian van der Voort , Fatih Incekara , Marion Smits , Stefan Klein

Convolutional Neural Networks (CNNs) have recently emerged as the dominant model in computer vision. If provided with enough training data, they predict almost any visual quantity. In a discrete setting, such as classification, CNNs are not…

Computer Vision and Pattern Recognition · Computer Science 2015-11-25 Deepak Pathak , Philipp Krähenbühl , Stella X. Yu , Trevor Darrell

Batch-Normalization (BN) layers have become fundamental components in the evermore complex deep neural network architectures. Such models require acceleration processes for deployment on edge devices. However, BN layers add computation…

Machine Learning · Computer Science 2022-03-29 Edouard Yvinec , Arnaud Dapogny , Kevin Bailly

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Machine Learning · Computer Science 2018-06-29 Alessandro Achille , Stefano Soatto

Comparing different neural network representations and determining how representations evolve over time remain challenging open questions in our understanding of the function of neural networks. Comparing representations in neural networks…

Machine Learning · Statistics 2018-10-25 Ari S. Morcos , Maithra Raghu , Samy Bengio

Batch Normalization (BN) and its variants have delivered tremendous success in combating the covariate shift induced by the training step of deep learning methods. While these techniques normalize feature distributions by standardizing with…

Machine Learning · Computer Science 2021-05-06 Mandy Lu , Qingyu Zhao , Jiequan Zhang , Kilian M. Pohl , Li Fei-Fei , Juan Carlos Niebles , Ehsan Adeli

To adapt to real-world data streams, continual learning (CL) systems must rapidly learn new concepts while preserving and utilizing prior knowledge. When it comes to adding new information to continually-trained deep neural networks (DNNs),…

Machine Learning · Computer Science 2025-07-02 Md Yousuf Harun , Christopher Kanan

Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions. In this paper, we demonstrate properly…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Yuhui Xu , Lingxi Xie , Cihang Xie , Jieru Mei , Siyuan Qiao , Wei Shen , Hongkai Xiong , Alan Yuille

Batch normalization (BN) is a key facilitator and considered essential for state-of-the-art binary neural networks (BNN). However, the BN layer is costly to calculate and is typically implemented with non-binary parameters, leaving a hurdle…

Machine Learning · Computer Science 2021-04-19 Tianlong Chen , Zhenyu Zhang , Xu Ouyang , Zechun Liu , Zhiqiang Shen , Zhangyang Wang

A persistent paradox in continual learning (CL) is that neural networks often retain linearly separable representations of past tasks even when their output predictions fail. We formalize this distinction as the gap between deep…

Machine Learning · Computer Science 2026-03-20 Giulia Lanzillotta , Damiano Meier , Thomas Hofmann

Convolutional neural networks (CNNs) are similar to "ordinary" neural networks in the sense that they are made up of hidden layers consisting of neurons with "learnable" parameters. These neurons receive inputs, performs a dot product, and…

Computer Vision and Pattern Recognition · Computer Science 2019-02-08 Abien Fred Agarap
‹ Prev 1 8 9 10 Next ›