On the Power and Limitations of Random Features for Understanding Neural Networks

Feb-12-2026, 05:19:10 GMT–Neural Information Processing Systems

Considering the one-hidden-layer example above, this corresponds to learning linear predictors over a fixed representation (chosen obliviously and randomly at initialization).

artificial intelligence, machine learning, neural network, (16 more...)

Neural Information Processing Systems

Feb-12-2026, 05:19:10 GMT

Conferences PDF

Country:
- Asia > Middle East
  - Jordan (0.04)
- Europe > United Kingdom
  - England > Cambridgeshire > Cambridge (0.04)
- North America > Canada (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning
  - Neural Networks > Deep Learning (0.46)
  - Statistical Learning > Gradient Descent (0.31)

Duplicate Docs Excel Report

Title
On the Power and Limitations of Random Features for Understanding Neural Networks

Similar Docs Excel Report more

Title	Similarity	Source
None found