2 Method Notations We use X>, X1, Tr(X) and vec(X) to denote the transpose, inverse, trace, and column-wise vectorization of amatrixX. We use X Y to represent the Kronecker product

Neural Information Processing Systems 

In contrast, artificial agents are prone to'catastrophic forgetting' whereby performance on previous tasks deteriorates rapidly as new ones are acquired. This shortcoming has recently been addressed using methods that encourage parameters tostay close tothose used forprevious tasks.