State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictions
Wang, Cheng, Lawrence, Carolin, Niepert, Mathias
–arXiv.org Artificial Intelligence
Recurrent neural networks are a widely used class of neural architectures. They have, however, two shortcomings. First, they are often treated as black-box models and as such it is difficult to understand what exactly they learn as well as how they arrive at a particular prediction. 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) non-regular languages such as balanced parentheses and palindromes where external memory is required; and (3) real-word sequence learning tasks for sentiment analysis, visual object recognition and text categorisation. We show that state-regularization (a) simplifies the extraction of finite state automata that display an RNN's state transition dynamic; (b) forces RNNs to operate more like automata with external memory and less like finite state machines, which potentiality leads to a more structural memory; (c) leads to better interpretability and explainability of RNNs by leveraging the probabilistic finite state transition mechanism over time steps.
arXiv.org Artificial Intelligence
Dec-9-2022
- Country:
- North America > United States
- Indiana (0.04)
- Washington > King County
- Seattle (0.04)
- Oregon > Multnomah County
- Portland (0.04)
- California > Santa Clara County
- Palo Alto (0.04)
- Europe > Germany
- Brandenburg > Potsdam (0.04)
- Berlin (0.04)
- Baden-Württemberg
- Stuttgart Region > Stuttgart (0.04)
- Karlsruhe Region > Heidelberg (0.04)
- Asia > Middle East
- Jordan (0.04)
- North America > United States
- Genre:
- Research Report (0.82)
- Industry:
- Government (0.31)
- Technology: