no code implementations • 30 Apr 2024 • Lorenzo Pes, Rick Luiken, Federico Corradi, Charlotte Frenkel
While the human brain efficiently adapts to new tasks from a continuous stream of information, neural network models struggle to learn from sequential information without catastrophically forgetting previously learned tasks.
no code implementations • 11 Apr 2023 • Thomas Ortner, Lorenzo Pes, Joris Gentinetta, Charlotte Frenkel, Angeliki Pantazi
Recurrent neural networks trained with the backpropagation through time (BPTT) algorithm have led to astounding successes in various temporal tasks.