Extracting automata from neural networks using active learning

@article{Xu2021ExtractingAF,
  title={Extracting automata from neural networks using active learning},
  author={Zhiwu Xu and Cheng Wen and S. Qin and Mengda He},
  journal={PeerJ Computer Science},
  year={2021},
  volume={7}
}
Deep learning is one of the most advanced forms of machine learning. Most modern deep learning models are based on an artificial neural network, and benchmarking studies reveal that neural networks have produced results comparable to and in some cases superior to human experts. However, the generated neural networks are typically regarded as incomprehensible black-box models, which not only limits their applications, but also hinders testing and verifying. In this paper, we present an active… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 37 REFERENCES
Extraction of rules from discrete-time recurrent neural networks
TLDR
The focus of this paper is on the quality of the rules that are extracted from recurrent neural networks, and a heuristic is introduced that permits us to choose among the consistent DFAs the model which best approximates the learned regular grammar. Expand
Symbolic Knowledge Representation in Recurrent Neural Networks: Insights from Theoretical Models of
TLDR
This chapter addresses some fundamental issues in regard to recurrent neural network architectures and learning algorithms, their computational power, their suitability for diierent classes of applications, and their ability to acquire symbolic knowledge through learning. Expand
Learning Finite State Machines With Self-Clustering Recurrent Networks
TLDR
This paper proposes a new method to force a recurrent neural network to learn stable states by introducing discretization into the network and using a pseudo-gradient learning rule to perform training, which has similar capabilities in learning finite state automata as the original network, but without the instability problem. Expand
Intriguing properties of neural networks
TLDR
It is found that there is no distinction between individual highlevel units and random linear combinations of high level units, according to various methods of unit analysis, and it is suggested that it is the space, rather than the individual units, that contains of the semantic information in the high layers of neural networks. Expand
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
We present a novel algorithm that uses exact learning and abstraction to extract a deterministic finite automaton describing the state dynamics of a given trained RNN. We do this using Angluin's L*Expand
Rule Extraction from Recurrent Neural Networks: ATaxonomy and Review
TLDR
This article reviews the progress of techniques for extraction of rules from RNNs and develops a taxonomy specifically designed for this purpose, and identifies important open research issues that can give the field a significant push forward. Expand
Deep learning in neural networks: An overview
TLDR
This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks. Expand
Inductive inference from noisy examples using the hybrid finite state filter
TLDR
A training algorithm, referred to as hybrid finite state filter (HFF), which is based on a parsimony principle that penalizes the development of complex rules, while removing noise is proposed. Expand
Inducing Regular Grammars Using Recurrent Neural Networks
TLDR
This work trains a recurrent neural network to distinguish between strings that are in or outside a regular language, and utilizes an algorithm for extracting the learned finite-state automaton. Expand
Learning with Interpretable Structure from RNN
TLDR
It is found that Finite State Automaton (FSA) that processes sequential data has more interpretable inner mechanism and can be learned from RNNs as the interpretable structure and the transitions in FSA leading to specific classification result are associated with corresponding words which are understandable by human beings. Expand
...
1
2
3
4
...