This repository is a curated list of papers exploring empirical studies and insights into deep learning phenomena. It aims to bridge the gap between the practical success of neural networks and theoretical understanding, serving researchers and practitioners interested in the underlying mechanisms of deep learning.

How It Works

The collection is organized by key phenomena observed in deep learning, such as Neural Collapse, Deep Double Descent, and the Lottery Ticket Hypothesis. Each entry includes a paper title, a link to the paper, authors, publication venue, relevant keywords, and a concise digest summarizing the paper's core findings and contributions.

Quick Start & Requirements

No installation or execution is required. This is a reference list.

Highlighted Details

• Comprehensive coverage of major deep learning phenomena.
• Continually updated with new research.
• Includes papers from top-tier conferences and journals.
• Provides digests for quick understanding of paper content.

Maintenance & Community

The list is maintained by MinghuiChen43 and welcomes contributions via GitHub issues or direct contact.

Licensing & Compatibility

This repository is a collection of links to external research papers and does not have its own license. Compatibility depends on the licenses of the linked papers.

Limitations & Caveats

The list is a curated collection and may not be exhaustive. The quality and accessibility of the linked papers vary.