Francesco Lässig
Francesco Lässig
About
Publications
Experience
Contents
Education
Light
Dark
Automatic
Deep Learning
Bio-Inspired, Task-Free Continual Learning through Activity Regularization
This work puts forward a novel continual learning algorithm based on brain-inspired principles of neural computation. Contrary to many existing approaches, our method does not make use of task boundaries or data replay.
Francesco Lässig
,
Pau Vilimelis Aceituno
,
Martino Sorbaro
,
Benjamin F. Grewe
PDF
Cite
Code
DOI
Biological Cybernetics
arXiv
Temporal Convolutional Networks and Forecasting
How a convolutional network with some simple adaptations can become a powerful tool for sequence modeling and forecasting.
Last updated on Dec 29, 2022
Posts
,
Darts
Cite
×