4 results for "Timo Flesch"
Showing 1–4 · 0.42 seconds · RSS
-
Journal Article Full text
Orthogonal representations for robust context-dependent task performance in brains and neural networks
How do neural populations code for multiple, potentially conflicting tasks? Here we used computational simulations involving neural networks to define "lazy" and "rich" coding solutions to this context-dependent decision-making problem, which trade off learning speed for robustness. During lazy…
-
Journal Article Full text
Modelling continual learning in humans with Hebbian context gating and exponentially decaying task signals
Humans can learn several tasks in succession with minimal mutual interference but perform more poorly when trained on multiple tasks at once. The opposite is true for standard deep neural networks. Here, we propose novel computational constraints for artificial neural networks, inspired by earlier…