Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
This work addresses memory management challenges in neural networks for tasks like question answering, but it is incremental as it builds on existing NTM models.
The authors tackled the problem of improving memory addressing in neural Turing machines by introducing a dynamic neural Turing machine with trainable soft and hard addressing schemes, resulting in outperformance over NTM and LSTM baselines on Facebook bAbI tasks.
We extend neural Turing machine (NTM) model into a dynamic neural Turing machine (D-NTM) by introducing a trainable memory addressing scheme. This addressing scheme maintains for each memory cell two separate vectors, content and address vectors. This allows the D-NTM to learn a wide variety of location-based addressing strategies including both linear and nonlinear ones. We implement the D-NTM with both continuous, differentiable and discrete, non-differentiable read/write mechanisms. We investigate the mechanisms and effects of learning to read and write into a memory through experiments on Facebook bAbI tasks using both a feedforward and GRUcontroller. The D-NTM is evaluated on a set of Facebook bAbI tasks and shown to outperform NTM and LSTM baselines. We have done extensive analysis of our model and different variations of NTM on bAbI task. We also provide further experimental results on sequential pMNIST, Stanford Natural Language Inference, associative recall and copy tasks.