Metalearned Neural Memory
This work addresses the need for more flexible memory in neural networks for various learning problems, though it appears incremental as it builds on existing metalearning techniques.
The authors tackled the problem of enhancing recurrent neural networks with an external memory mechanism by conceptualizing it as a rapidly adaptable neural network function, achieving strong performance on tasks like supervised question answering and reinforcement learning.
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning. We conceptualize this memory as a rapidly adaptable function that we parameterize as a deep neural network. Reading from the neural memory function amounts to pushing an input (the key vector) through the function to produce an output (the value vector). Writing to memory means changing the function; specifically, updating the parameters of the neural network to encode desired information. We leverage training and algorithmic techniques from metalearning to update the neural memory function in one shot. The proposed memory-augmented model achieves strong performance on a variety of learning problems, from supervised question answering to reinforcement learning.