Decebal Constantin Mocanu

Learn about Dynamic Sparse Training and its benefits for neural network efficiency.

Examining how parameter isolation improves continual learning through dynamic sparse training methods.

FOCIL enables machines to learn without forgetting past knowledge effectively.

A new method helps robots learn from humans while ignoring distractions.

Sparse Neural Networks streamline feature selection for better model performance.

Exploring Sparse Neural Networks and their performance with challenging training data.