Idioma:

DeepLocalize: Fault Localization for Deep Neural Networks

Wardat, Mohammad ; Le, Wei ; Rajan, Hridesh

2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, p.251-262

Piscataway, NJ, USA: IEEE Press

Texto completo disponível

Citações Citado por

Enviar para

Título:
DeepLocalize: Fault Localization for Deep Neural Networks
Autor: Wardat, Mohammad ; Le, Wei ; Rajan, Hridesh
Assuntos: Benchmark testing ; Computer bugs ; Computing methodologies ; Computing methodologies -- Machine learning ; Computing methodologies -- Machine learning -- Machine learning approaches ; Debugging ; Deep learning bugs ; Deep Neural Networks ; Fault diagnosis ; Fault Location ; Neural networks ; Numerical models ; Program Analysis ; Software and its engineering ; Software and its engineering -- Software creation and management ; Software and its engineering -- Software creation and management -- Software verification and validation ; Software and its engineering -- Software creation and management -- Software verification and validation -- Software defect analysis ; Software and its engineering -- Software creation and management -- Software verification and validation -- Software defect analysis -- Software testing and debugging ; Software and its engineering -- Software organization and properties ; Theory of computation
É parte de: 2021 IEEE/ACM 43rd International Conference on Software Engineering (ICSE), 2021, p.251-262
Descrição: Deep neural networks (DNNs) are becoming an integral part of most software systems. Previous work has shown that DNNs have bugs. Unfortunately, existing debugging techniques don't support localizing DNN bugs because of the lack of understanding of model behaviors. The entire DNN model appears as a black box. To address these problems, we propose an approach and a tool that automatically determines whether the model is buggy or not, and identifies the root causes for DNN errors. Our key insight is that historic trends in values propagated between layers can be analyzed to identify faults, and also localize faults. To that end, we first enable dynamic analysis of deep learning applications: by converting it into an imperative representation and alternatively using a callback mechanism. Both mechanisms allows us to insert probes that enable dynamic analysis over the traces produced by the DNN while it is being trained on the training data. We then conduct dynamic analysis over the traces to identify the faulty layer or hyperparameter that causes the error. We propose an algorithm for identifying root causes by capturing any numerical error and monitoring the model during training and finding the relevance of every layer/parameter on the DNN outcome. We have collected a benchmark containing 40 buggy models and patches that contain real errors in deep learning applications from Stack Overflow and GitHub. Our benchmark can be used to evaluate automated debugging tools and repair techniques. We have evaluated our approach using this DNN bug-and-patch benchmark, and the results showed that our approach is much more effective than the existing debugging approach used in the state-of-the-practice Keras library. For 34/40 cases, our approach was able to detect faults whereas the best debugging approach provided by Keras detected 32/40 faults. Our approach was able to localize 21/40 bugs whereas Keras did not localize any faults.
Editor: Piscataway, NJ, USA: IEEE Press
Idioma: Inglês

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

DeepLocalize: Fault Localization for Deep Neural Networks

Wardat, Mohammad ; Le, Wei ; Rajan, Hridesh

Piscataway, NJ, USA: IEEE Press

Buscando em bases de dados remotas. Favor aguardar.