中文
相关论文

相关论文: Neural Collapse in Cumulative Link Models for Ordi…

200 篇论文

The modern strategy for training deep neural networks for classification tasks includes optimizing the network's weights even after the training error vanishes to further push the training loss toward zero. Recently, a phenomenon termed…

机器学习 · 计算机科学 2022-10-13 Tom Tirer , Joan Bruna

Neural collapse (NC) refers to the surprising structure of the last layer of deep neural networks in the terminal phase of gradient descent training. Recently, an increasing amount of experimental evidence has pointed to the propagation of…

机器学习 · 计算机科学 2023-05-23 Peter Súkeník , Marco Mondelli , Christoph Lampert

Recently it has been observed that neural networks exhibit Neural Collapse (NC) during the final stage of training for the classification problem. We empirically show that multivariate regression, as employed in imitation learning and other…

机器学习 · 计算机科学 2025-09-30 George Andriopoulos , Zixuan Dong , Li Guo , Zifan Zhao , Keith Ross

Neural collapse (NC) is a phenomenon that emerges at the terminal phase of the training (TPT) of deep neural networks (DNNs). The features of the data in the same class collapse to their respective sample means and the sample means exhibit…

机器学习 · 统计学 2024-09-09 Wanli Hong , Shuyang Ling

The current paradigm of training deep neural networks for classification tasks includes minimizing the empirical risk that pushes the training loss value towards zero, even after the training error has been vanished. In this terminal phase…

机器学习 · 计算机科学 2024-06-07 Hien Dang , Tho Tran , Tan Nguyen , Nhat Ho

Recent years have witnessed the huge success of deep neural networks (DNNs) in various tasks of computer vision and text processing. Interestingly, these DNNs with massive number of parameters share similar structural properties on their…

机器学习 · 统计学 2023-10-26 Wanli Hong , Shuyang Ling

Neural Collapse is a phenomenon where the last-layer representations of a well-trained neural network converge to a highly structured geometry. In this paper, we focus on its first (and most basic) property, known as NC1: the within-class…

机器学习 · 计算机科学 2025-02-05 Diyuan Wu , Marco Mondelli

Recent findings reveal that over-parameterized deep neural networks, trained beyond zero training-error, exhibit a distinctive structural pattern at the final layer, termed as Neural-collapse (NC). These results indicate that the final…

机器学习 · 计算机科学 2024-03-01 Tina Behnia , Christos Thrampoulidis

Modern deep neural networks have achieved impressive performance on tasks from image classification to natural language processing. Surprisingly, these complex systems with massive amounts of parameters exhibit the same structural…

机器学习 · 计算机科学 2023-06-21 Hien Dang , Tho Tran , Stanley Osher , Hung Tran-The , Nhat Ho , Tan Nguyen

Deep neural networks (DNNs) exhibit a surprising structure in their final layer known as neural collapse (NC), and a growing body of works has currently investigated the propagation of neural collapse to earlier layers of DNNs -- a…

机器学习 · 计算机科学 2024-10-22 Peter Súkeník , Marco Mondelli , Christoph Lampert

Neural Collapse is a phenomenon that helps identify sparse and low rank structures in deep classifiers. Recent work has extended the definition of neural collapse to regression problems, albeit only measuring the phenomenon at the last…

机器学习 · 计算机科学 2026-03-26 Akshay Rangamani , Altay Unal

Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be suboptimal in deep architectures, attributing this to an explicit low-rank bias from L2…

机器学习 · 计算机科学 2026-05-25 Connall Garrod , Jonathan P. Keating , Christos Thrampoulidis

Graph neural networks (GNNs) have become increasingly popular for classification tasks on graph-structured data. Yet, the interplay between graph topology and feature evolution in GNNs is not well understood. In this paper, we focus on…

机器学习 · 计算机科学 2023-10-27 Vignesh Kothapalli , Tom Tirer , Joan Bruna

Among many mysteries behind the success of deep networks lies the exceptional discriminative power of their learned representations as manifested by the intriguing Neural Collapse (NC) phenomenon, where simple feature structures emerge at…

机器学习 · 计算机科学 2025-10-27 Hancheng Min , Zhihui Zhu , René Vidal

The recently discovered Neural Collapse (NC) phenomenon occurs pervasively in today's deep net training paradigm of driving cross-entropy (CE) loss towards zero. During NC, last-layer features collapse to their class-means, both classifiers…

机器学习 · 计算机科学 2022-05-11 X. Y. Han , Vardan Papyan , David L. Donoho

Neural collapse (NC) and its multi-layer variant, deep neural collapse (DNC), describe a structured geometry that occurs in the features and weights of trained deep networks. Recent theoretical work by Sukenik et al. using a deep…

机器学习 · 计算机科学 2025-10-07 Connall Garrod , Jonathan P. Keating

Neural Collapse (NC) gives a precise description of the representations of classes in the final hidden layer of classification neural networks. This description provides insights into how these networks learn features and generalize well…

机器学习 · 计算机科学 2023-08-08 Liam Parker , Emre Onal , Anton Stengel , Jake Intrater

Neural collapse (NC) is a simple and symmetric phenomenon for deep neural networks (DNNs) at the terminal phase of training, where the last-layer features collapse to their class means and form a simplex equiangular tight frame aligning…

机器学习 · 计算机科学 2024-05-03 Sicong Wang , Kuo Gai , Shihua Zhang

Neural collapse (NC) -- the convergence of penultimate-layer features to a simplex equiangular tight frame -- is well understood at equilibrium, but the dynamics governing its onset remain poorly characterised. We identify a simple and…

机器学习 · 计算机科学 2026-04-02 Anamika Paul Rupa

When training deep neural networks for classification tasks, an intriguing empirical phenomenon has been widely observed in the last-layer classifiers and features, where (i) the class means and the last-layer classifiers all collapse to…

机器学习 · 计算机科学 2022-03-15 Jinxin Zhou , Xiao Li , Tianyu Ding , Chong You , Qing Qu , Zhihui Zhu
‹ 上一页 1 2 3 10 下一页 ›