2019
Improving Differentiable Neural Computers Through Memory Masking, De-allocation, and Link Distribution Sharpness Control
ICLR 2019poster
The Differentiable Neural Computer (DNC) can learn algorithmic and question answering tasks. An analysis of its internal activation patterns reveals three problems: Most importantly, the lack of key-value separation makes the address distribution resulting from content-based look-up noisy and flat,…