Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
continuous_learning [2018/10/18 10:41]
admin
continuous_learning [2018/12/29 12:58] (current)
admin
Line 20: Line 20:
 Here, we studied the patterns of errors made by humans and state-of-the-art neural networks while they learned new tasks from scratch and without instruction. Humans, but not machines, seem to benefit from training regimes that blocked one task at a time, especially when they had a prior bias to represent stimuli in a way that encouraged task separation. Machines trained to exhibit the same prior bias suffered less interference between tasks, suggesting new avenues for solving continual learning in artificial systems. Here, we studied the patterns of errors made by humans and state-of-the-art neural networks while they learned new tasks from scratch and without instruction. Humans, but not machines, seem to benefit from training regimes that blocked one task at a time, especially when they had a prior bias to represent stimuli in a way that encouraged task separation. Machines trained to exhibit the same prior bias suffered less interference between tasks, suggesting new avenues for solving continual learning in artificial systems.
  
 +https://​arxiv.org/​abs/​1805.06370v2 Progress & Compress: A scalable framework for continual learning¬†
 +