State-Regularized Recurrent Neural Networks
This addresses interpretability and memory issues in RNNs for sequence learning tasks, but it is incremental as it builds on existing RNN architectures.
The paper tackled the problems of poor interpretability and long-term memorization in recurrent neural networks by introducing state-regularization, a stochastic mechanism that transitions between learnable states, resulting in improved performance on tasks like balanced parentheses and language modeling.
Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, it is difficult to understand what exactly they learn. Second, they tend to work poorly on sequences requiring long-term memorization, despite having this capacity in principle. We aim to address both shortcomings with a class of recurrent networks that use a stochastic state transition mechanism between cell applications. This mechanism, which we term state-regularization, makes RNNs transition between a finite set of learnable states. We evaluate state-regularized RNNs on (1) regular languages for the purpose of automata extraction; (2) nonregular languages such as balanced parentheses, palindromes, and the copy task where external memory is required; and (3) real-word sequence learning tasks for sentiment analysis, visual object recognition, and language modeling. We show that state-regularization (a) simplifies the extraction of finite state automata modeling an RNN's state transition dynamics; (b) forces RNNs to operate more like automata with external memory and less like finite state machines; (c) makes RNNs have better interpretability and explainability.