DeepCover: Advancing RNN Test Coverage and Online Error Prediction using State Machine Extraction

Abstract

Recurrent neural networks (RNNs) have emerged as powerful tools for processing sequential data in various fields, including natural language processing and speech recognition. However, the lack of explainability in RNN models has limited their interpretability, posing challenges in understanding their internal workings. To address this issue, this paper proposes a methodology for extracting a state machine (SM) from an RNN-based model to provide insights into its internal function. The proposed SM extraction algorithm was assessed using four newly proposed metrics: Purity, Richness, Goodness, and Scale. The proposed methodology along with its assessment metrics contribute to increasing explainability in RNN models by providing a clear representation of their internal decision making process through the extracted SM. In addition to improving the explainability of RNNs, the extracted SM can be used to advance testing and and monitoring of the primary RNN-based model. To enhance RNN testing, we introduce six model coverage criteria based on the extracted SM, serving as metrics for evaluating the effectiveness of test suites designed to analyze the primary model. We also propose a tree-based model to predict the error probability of the primary model for each input based on the extracted SM. We evaluated our proposed online error prediction approach using the MNIST dataset and Mini Speech Commands dataset, achieving an area under the curve (AUC) exceeding 80\% for the receiver operating characteristic (ROC) chart.

References in corpus (9)

• Neural Machine Translation by Jointly Learning to Align and Translate
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
• DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems
• Certified Defenses against Adversarial Examples
• Entropy-based Logic Explanations of Neural Networks
• Increasing the Confidence of Deep Neural Networks by Coverage Analysis
• A Probabilistic Framework for Mutation Testing in Deep Neural Networks