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 …

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) …

Neural circuits—both in the brain and in “artificial” neural network models—learn to solve a
remarkable variety of tasks, and there is a great current opportunity to use neural networks …

While cross entropy (CE) is the most commonly used loss function to train deep neural
networks for classification tasks, many alternative losses have been developed to obtain …

Neural Collapse refers to the remarkable structural properties characterizing the geometry of
class embeddings and classifier weights, found by deep nets when trained beyond zero …

This work attempts to provide a plausible theoretical framework that aims to interpret modern
deep (convolutional) networks from the principles of data compression and discriminative …

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear
what characteristics of their representations lead to high downstream accuracies. In this …

When training overparameterized deep networks for classification tasks, it has been widely
observed that the learned features exhibit a so-called" neural collapse'" phenomenon. More …

Sharpness-aware minimization (SAM) is a recently proposed method that minimizes the
sharpness of the training loss of a neural network. While its generalization improvement is …

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 …