Exact natural gradient in deep linear networks and its application to the nonlinear case

Alberto Bernacchia, Mate Lengyel, Guillaume Hennequin

Nov-18-2025, 02:08:16 GMT–Neural Information Processing Systems

Stochastic gradient descent (SGD) is used ubiquitously to train deep neural networks, due to its low computational cost and ease of implementation.

artificial intelligence, gradient, machine learning, (18 more...)

Neural Information Processing Systems

Nov-18-2025, 02:08:16 GMT

Conferences PDF

Country:
- Europe
  - Hungary > Budapest
    - Budapest (0.04)
  - United Kingdom > England
    - Cambridgeshire > Cambridge (0.14)
- North America > Canada
  - Quebec > Montreal (0.04)

Technology:
- Information Technology > Artificial Intelligence
  - Machine Learning
    - Neural Networks (1.00)
    - Statistical Learning > Gradient Descent (0.71)
  - Representation & Reasoning (1.00)

Duplicate Docs Excel Report

Title
Exact natural gradient in deep linear networks and its application to the nonlinear case
Exact natural gradient in deep linear networks and its application to the nonlinear case

Similar Docs Excel Report more

Title	Similarity	Source
None found