Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice

Jeffrey Pennington, Samuel Schoenholz, Surya Ganguli

Nov-21-2025, 13:08:39 GMT–Neural Information Processing Systems

However, it is unclear how to achieve dynamical isometry in nonlinear deep networks.

artificial intelligence, dynamical isometry, machine learning, (15 more...)

Neural Information Processing Systems

Nov-21-2025, 13:08:39 GMT

Conferences PDF

Country:
- North America > United States
  - California > Los Angeles County
    - Long Beach (0.04)
  - Rhode Island > Providence County
    - Providence (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)

Duplicate Docs Excel Report

Title
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice
Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice

Similar Docs Excel Report more

Title	Similarity	Source
None found