Neural Stored-program Memory

ICLR 2020  ·  Hung Le, Truyen Tran, Svetha Venkatesh ·

Neural networks powered with external memory simulate computer behaviors. These models, which use the memory to store data for a neural controller, can learn algorithms and other complex tasks. In this paper, we introduce a new memory to store weights for the controller, analogous to the stored-program memory in modern computer architectures. The proposed model, dubbed Neural Stored-program Memory, augments current memory-augmented neural networks, creating differentiable machines that can switch programs through time, adapt to variable contexts and thus resemble the Universal Turing Machine. A wide range of experiments demonstrate that the resulting machines not only excel in classical algorithmic problems, but also have potential for compositional, continual, few-shot learning and question-answering tasks.

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract

Datasets


Results from the Paper


Ranked #5 on Question Answering on bAbi (Mean Error Rate metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Question Answering bAbi NUTM Mean Error Rate 5.6% # 5

Methods


No methods listed for this paper. Add relevant methods here