中文
相关论文

相关论文: Neural Collapse in the Intermediate Hidden Layers …

200 篇论文

Understanding the per-layer learning dynamics of deep neural networks is of significant interest as it may provide insights into how neural networks learn and the potential for better training regimens. We investigate learning in Deep…

机器学习 · 计算机科学 2020-12-02 Ayush Manish Agrawal , Atharva Tendle , Harshvardhan Sikka , Sahib Singh , Amr Kayid

Neural collapse is an emergent phenomenon in deep learning that was recently discovered by Papyan, Han and Donoho. We propose a simple "unconstrained features model" in which neural collapse also emerges empirically. By studying this model,…

机器学习 · 计算机科学 2020-11-24 Dustin G. Mixon , Hans Parshall , Jianzong Pi

Deep neural networks progressively transform their inputs across multiple processing layers. What are the geometrical properties of the representations learned by these networks? Here we study the intrinsic dimensionality (ID) of…

机器学习 · 计算机科学 2019-10-29 Alessio Ansuini , Alessandro Laio , Jakob H. Macke , Davide Zoccolan

Deep neural networks can empirically perform efficient hierarchical learning, in which the layers learn useful representations of the data. However, how they make use of the intermediate representations are not explained by recent theories…

机器学习 · 计算机科学 2021-03-08 Minshuo Chen , Yu Bai , Jason D. Lee , Tuo Zhao , Huan Wang , Caiming Xiong , Richard Socher

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC), a powerful empirical and theoretical framework which…

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

The Convolutional Neural Networks (CNNs), in domains like computer vision, mostly reduced the need for handcrafted features due to its ability to learn the problem-specific features from the raw input data. However, the selection of…

计算机视觉与模式识别 · 计算机科学 2019-11-20 S. H. Shabbeer Basha , Shiv Ram Dubey , Viswanath Pulabaigari , Snehasis Mukherjee

In this paper, we provide an overview of a common phenomenon, condensation, observed during the nonlinear training of neural networks: During the nonlinear training of neural networks, neurons in the same layer tend to condense into groups…

机器学习 · 计算机科学 2026-04-14 Zhi-Qin John Xu , Yaoyu Zhang , Zhangchen Zhou

We propose a one-class neural network (OC-NN) model to detect anomalies in complex data sets. OC-NN combines the ability of deep networks to extract a progressively rich representation of data with the one-class objective of creating a…

机器学习 · 计算机科学 2019-01-14 Raghavendra Chalapathy , Aditya Krishna Menon , Sanjay Chawla

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

Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of more effective networks, which results in a complexification of their architectures with more layers,…

机器学习 · 计算机科学 2019-11-14 A. Deliege , A. Cioppa , M. Van Droogenbroeck

Although 3D point cloud classification neural network models have been widely used, the in-depth interpretation of the activation of the neurons and layers is still a challenge. We propose a novel approach, named Relevance Flow, to…

计算机视觉与模式识别 · 计算机科学 2023-03-14 Weiquan Liu , Minghao Liu , Shijun Zheng , Cheng Wang

Future wireless networks are expected to be AI-empowered, making their performance highly dependent on the quality of training datasets. However, physical-layer entities often observe only partial wireless environments characterized by…

信号处理 · 电气工程与系统科学 2025-06-25 Kaidi Xu , Shenglong Zhou , Geoffrey Ye Li

Deep classifiers are known to be sensitive to data distribution shifts, primarily due to their reliance on spurious correlations in training data. It has been suggested that these classifiers can still find useful features in the network's…

机器学习 · 计算机科学 2025-04-09 Arnas Uselis , Seong Joon Oh

With the substantial performance of neural networks in sensitive fields increases the need for interpretable deep learning models. Major challenge is to uncover the multiscale and distributed representation hidden inside the basket mappings…

计算机视觉与模式识别 · 计算机科学 2022-11-10 Piduguralla Manaswini , Jignesh S. Bhatt

While deep learning has enabled significant advances in many areas of science, its black-box nature hinders architecture design for future artificial intelligence applications and interpretation for high-stakes decision makings. We…

机器学习 · 计算机科学 2023-08-14 Hangfeng He , Weijie J. Su

Deep regression models typically learn in an end-to-end fashion without explicitly emphasizing a regression-aware representation. Consequently, the learned representations exhibit fragmentation and fail to capture the continuous nature of…

机器学习 · 计算机科学 2023-10-11 Kaiwen Zha , Peng Cao , Jeany Son , Yuzhe Yang , Dina Katabi

Deep Neural Collapse (DNC) refers to the surprisingly rigid structure of the data representations in the final layers of Deep Neural Networks (DNNs). Though the phenomenon has been measured in a variety of settings, its emergence is…

机器学习 · 计算机科学 2025-01-22 Daniel Beaglehole , Peter Súkeník , Marco Mondelli , Mikhail Belkin

We analyze the loss landscape and expressiveness of practical deep convolutional neural networks (CNNs) with shared weights and max pooling layers. We show that such CNNs produce linearly independent features at a "wide" layer which has…

机器学习 · 计算机科学 2018-06-07 Quynh Nguyen , Matthias Hein

We propose a general framework called Network Dissection for quantifying the interpretability of latent representations of CNNs by evaluating the alignment between individual hidden units and a set of semantic concepts. Given any CNN model,…

计算机视觉与模式识别 · 计算机科学 2017-04-20 David Bau , Bolei Zhou , Aditya Khosla , Aude Oliva , Antonio Torralba

Deep convolutional neural networks (CNNs) trained on objects and scenes have shown intriguing ability to predict some response properties of visual cortical neurons. However, the factors and computations that give rise to such ability, and…

神经元与认知 · 定量生物学 2018-06-11 Md Nasir Uddin Laskar , Luis G Sanchez Giraldo , Odelia Schwartz