Hybrid computing using a neural network with dynamic external memory

Abstract

Artificial neural networks are remarkably adept at sensory processing, sequence learning and reinforcement learning, but are limited in their ability to represent variables and data structures and to store data over long timescales, owing to the lack of an external memory. Here we introduce a machine learning model called a differentiable neural computer (DNC), which consists of a neural network that can read from and write to an external memory matrix, analogous to the random-access memory in a conventional computer. Like a conventional computer, it can use its memory to represent and manipulate complex data structures, but, like a neural network, it can learn to do so from data. When trained with supervised learning, we demonstrate that a DNC can successfully answer synthetic questions designed to emulate reasoning and inference problems in natural language. We show that it can learn tasks such as finding the shortest path between specified points and inferring the missing links in randomly generated graphs, and then generalize these tasks to specific graphs such as transport networks and family trees. When trained with reinforcement learning, a DNC can complete a moving blocks puzzle in which changing goals are specified by sequences of symbols. Taken together, our results demonstrate that DNCs have the capacity to solve complex, structured tasks that are inaccessible to neural networks without external read-write memory.

Transition-Based Dependency Parsing with Stack Long Short-Term Memory

“…However, this could be reversed, giving a device that learns to construct context-free programs (e.g., expression trees) given only observed outputs; one application would be unsupervised parsing. Such an extension of the work would make it an alternative to architectures that have an explicit external memory such as neural Turing machines (Graves et al, 2014) and memory networks (Weston et al, 2015). However, as with those models, without supervision of the stack operations, formidable computational challenges must be solved (e.g., marginalizing over all latent stack operations), but sampling techniques and techniques from reinforcement learning have promise here (Zaremba and Sutskever, 2015), making this an intriguing avenue for future work.…”

Recurrent Attention Network on Memory for Aspect Sentiment Analysis

“…Nevertheless, TD-LSTM might not work well when the opinion word is far from the target, because the captured feature is likely to be lost ( reported similar problems of LSTM-based models in machine translation). (Graves et al, 2014) introduced the concept of memory for NNs and proposed a differentiable process to read and write memory, which is called Neural Turing Machine (NTM). Attention mechanism, which has been used successfully in many areas Rush et al, 2015), can be treated as a simplified version of NTM because the size of memory is unlimited and we only need to read from it.…”

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

“…This distinguishes the keyvariable memory from other memory-augmented neural networks that use continuous differentiable embeddings as the values of memory entries (Weston et al, 2014;Graves et al, 2016a).…”