Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks

Aaron Voelker, Ivana Kajić, Chris Eliasmith

Feb-13-2026, 00:12:39 GMT–Neural Information Processing Systems

LSTMs are designed to help alleviate the issue of vanishing and exploding gradients commonly associatedwithtrainingRNNs[5].

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

Neural Information Processing Systems

Feb-13-2026, 00:12:39 GMT

Conferences PDF

Country:
- North America > Canada
  - British Columbia > Metro Vancouver Regional District
    - Vancouver (0.04)
  - Ontario > Waterloo Region
    - Waterloo (0.04)

Technology:
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.72)

Duplicate Docs Excel Report

Title
Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks

Similar Docs Excel Report more

Title	Similarity	Source
None found