
Synthesizing Contextfree Grammars from Recurrent Neural Networks (Extended Version)
We present an algorithm for extracting a subclass of the context free gr...
read it

A Comparison of Rule Extraction for Different Recurrent Neural Network Models and Grammatical Complexity
It has been shown that rules can be extracted from highly nonlinear, re...
read it

Learning with Interpretable Structure from RNN
In structure learning, the output is generally a structure that is used ...
read it

Stability of Internal States in Recurrent Neural Networks Trained on Regular Languages
We provide an empirical study of the stability of recurrent neural netwo...
read it

A Formal Language Approach to Explaining RNNs
This paper presents LEXR, a framework for explaining the decision making...
read it

Teaching Recurrent Neural Networks to Modify Chaotic Memories by Example
The ability to store and manipulate information is a hallmark of computa...
read it

Connecting First and Second Order Recurrent Networks with Deterministic Finite Automata
We propose an approach that connects recurrent networks with different o...
read it
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language. Specifically, we train a RNN on positive and negative examples from a regular language, and ask if there is a simple decoding function that maps states of this RNN to states of the minimal deterministic finite automaton (MDFA) for the language. Our experiments show that such a decoding function indeed exists, and that it maps states of the RNN not to MDFA states, but to states of an abstraction obtained by clustering small sets of MDFA states into "superstates". A qualitative analysis reveals that the abstraction often has a simple interpretation. Overall, the results suggest a strong structural relationship between internal representations used by RNNs and finite automata, and explain the wellknown ability of RNNs to recognize formal grammatical structure.
READ FULL TEXT
Comments
There are no comments yet.