mlsanityData to 14 Oct 2026

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

arXiv 2402.06966 ↗First posted 10 Feb 2024cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 52 references that are in the map. First posted on arXiv 10 Feb 2024.

Builds on

28 of 52 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  3. 2018Speech Commands: A Dataset for Limited-Vocabulary Speech Recognitioncited by 752
  4. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 669
  5. 2020Transformer Interpretability Beyond Attention Visualizationcited by 627
  6. 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
  7. 2018Certified Defenses against Adversarial Examplescited by 306
  8. 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
  9. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  10. 2015A Critical Review of Recurrent Neural Networks for Sequence Learningcited by 224
  11. 2015Inverting Visual Representations with Convolutional Networkscited by 170
  12. 2018DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systemscited by 147
16 more
  1. 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 124
  2. 2018On the Practical Computational Power of Finite Precision RNNs for Language Recognitioncited by 117
  3. 2018DeepMutation: Mutation Testing of Deep Learning Systemscited by 67
  4. 2017Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamplescited by 66
  5. 2020Depth Uncertainty in Neural Networkscited by 57
  6. 2019Sequential Neural Networks as Automatacited by 54
  7. 2018Concolic Testing for Deep Neural Networkscited by 51
  8. 2021Entropy-based Logic Explanations of Neural Networkscited by 51
  9. 2017Feature-Guided Black-Box Safety Testing of Deep Neural Networkscited by 49
  10. 2019Learning Deterministic Weighted Automata with Queries and Counterexamplescited by 22
  11. 2019Weighted Automata Extraction from Recurrent Neural Networks via Regression on State Spacescited by 21
  12. 2018Explaining Black Boxes on Sequential Data using Weighted Automatacited by 11
  13. 2022Extracting Weighted Finite Automata from Recurrent Neural Networks for Natural Languagescited by 10
  14. 2021Increasing the Confidence of Deep Neural Networks by Coverage Analysiscited by 9
  15. 2022A Probabilistic Framework for Mutation Testing in Deep Neural Networkscited by 3
  16. 2022State-Regularized Recurrent Neural Networks to Extract Automata and Explain Predictionscited by 2

Built on by

Not cited yet.