Learning Associative Inference Using Fast Weight Memory

Abstract

Humans can quickly associate stimuli to solve problems in novel contexts. Our novel neural network model learns state representations of facts that can be composed to perform such associative inference. To this end, we augment the LSTM model with an associative memory, dubbed Fast Weight Memory (FWM). Through differentiable operations at every step of a given input sequence, the LSTM updates and maintains compositional associations stored in the rapidly changing FWM weights. Our model is trained end-to-end by gradient descent and yields excellent performance on compositional language reasoning problems, meta-reinforcement-learning for POMDPs, and small-scale word-level language modelling.

References in corpus (6)

• Using Fast Weights to Attend to the Recent Past
• Neural Episodic Control
• Improving Generalization in Meta Reinforcement Learning using Learned Objectives
• Learning to generalize to new compositions in image understanding
• The Tensor Memory Hypothesis
• Learning to update Auto-associative Memory in Recurrent Neural Networks for Improving Sequence Memorization