|Jack Rae||DeepMind, UCL|
|Daan Wierstra||DeepMind Technologies|
|Oriol Vinyals||Google DeepMind|
|Razvan Pascanu||Google DeepMind|
|Timothy Lillicrap||Google DeepMind|
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods.
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to perform complex relational reasoning with the information they remember. Here, we first confirm our intuitions that standard memory architectures may struggle at tasks that heavily involve an understanding of the ways in which entities are connected -- i.e., tasks involving relational reasoning. We then improve upon these deficits by using a new memory module -- a Relational Memory Core (RMC) -- which employs multi-head dot product attention to allow memories to interact. Finally, we test the RMC on a suite of tasks that may profit from more capable relational reasoning across sequential information, and show large gains in RL domains (BoxWorld & Mini PacMan), program evaluation, and language modeling, achieving state-of-the-art results on the WikiText-103, Project Gutenberg, and GigaWord datasets.