中文
相关论文

相关论文: Prevalence of Neural Collapse during the terminal …

200 篇论文

Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the…

机器学习 · 计算机科学 2023-04-12 Vignesh Kothapalli

Neural collapse is a phenomenon observed during the terminal phase of neural network training, characterized by the convergence of network activations, class means, and linear classifier weights to a simplex equiangular tight frame (ETF), a…

机器学习 · 计算机科学 2024-12-03 Emily Liu

Neural Collapse (NC) is a well-known phenomenon of deep neural networks in the terminal phase of training (TPT). It is characterized by the collapse of features and classifier into a symmetrical structure, known as simplex equiangular tight…

机器学习 · 计算机科学 2023-10-13 Peifeng Gao , Qianqian Xu , Yibo Yang , Peisong Wen , Huiyang Shao , Zhiyong Yang , Bernard Ghanem , Qingming Huang

Neural Collapse (NC) is a recently observed phenomenon in neural networks that characterises the solution space of the final classifier layer when trained until zero training loss. Specifically, NC suggests that the final classifier layer…

机器学习 · 计算机科学 2024-11-05 Evan Markou , Thalaiyasingam Ajanthan , Stephen Gould

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

Modern deep neural networks for classification usually jointly learn a backbone for representation and a linear classifier to output the logit of each class. A recent study has shown a phenomenon called neural collapse that the within-class…

机器学习 · 计算机科学 2022-10-13 Yibo Yang , Shixiang Chen , Xiangtai Li , Liang Xie , Zhouchen Lin , Dacheng Tao

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

Training deep neural networks for classification often includes minimizing the training loss beyond the zero training error point. In this phase of training, a "neural collapse" behavior has been observed: the variability of features…

机器学习 · 计算机科学 2023-05-30 Tom Tirer , Haoxiang Huang , Jonathan Niles-Weed

Recent advances in theoretical Deep Learning have introduced geometric properties that occur during training, past the Interpolation Threshold -- where the training error reaches zero. We inquire into the phenomena coined Neural Collapse in…

机器学习 · 计算机科学 2022-06-14 Ido Ben-Shaul , Shai Dekel

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

The empirical emergence of neural collapse -- a surprising symmetry in the feature representations of the training data in the penultimate layer of deep neural networks -- has spurred a line of theoretical research aimed at its…

机器学习 · 计算机科学 2025-05-22 Peter Súkeník , Christoph H. Lampert , Marco Mondelli

There is a recently discovered and intriguing phenomenon called Neural Collapse: at the terminal phase of training a deep neural network for classification, the within-class penultimate feature means and the associated classifier vectors of…

计算机视觉与模式识别 · 计算机科学 2023-08-10 Tong Liang , Jim Davis

We provide the first global optimization landscape analysis of $Neural\;Collapse$ -- an intriguing empirical phenomenon that arises in the last-layer classifiers and features of neural networks during the terminal phase of training. As…

机器学习 · 计算机科学 2021-05-07 Zhihui Zhu , Tianyu Ding , Jinxin Zhou , Xiao Li , Chong You , Jeremias Sulam , Qing Qu

The recent work of Papyan, Han, & Donoho (2020) presented an intriguing "Neural Collapse" phenomenon, showing a structural property of interpolating classifiers in the late stage of training. This opened a rich area of exploration studying…

机器学习 · 计算机科学 2022-02-18 Like Hui , Mikhail Belkin , Preetum Nakkiran

Meta-learning frameworks for few-shot learning aims to learn models that can learn new skills or adapt to new environments rapidly with a few training examples. This has led to the generalizability of the developed model towards new classes…

机器学习 · 计算机科学 2023-10-10 Saaketh Medepalli , Naren Doraiswamy

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) -- 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

Recent studies have noted an intriguing phenomenon termed Neural Collapse, that is, when the neural networks establish the right correlation between feature spaces and the training targets, their last-layer features, together with the…

计算机视觉与模式识别 · 计算机科学 2025-09-22 Yining Wang , Junjie Sun , Chenyue Wang , Mi Zhang , Min Yang

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

The recently discovered Neural collapse (NC) phenomenon states that the last-layer weights of Deep Neural Networks (DNN), converge to the so-called Equiangular Tight Frame (ETF) simplex, at the terminal phase of their training. This ETF…

机器学习 · 计算机科学 2024-03-01 Hafiz Tiomoko Ali , Umberto Michieli , Ji Joong Moon , Daehyun Kim , Mete Ozay
‹ 上一页 1 2 3 10 下一页 ›