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 Kerns library. For 34/40 cases, our approach was able to detect faults whereas the best debugging approach provided by Kerns detected 32/40 faults. Our approach was able to localize 21/40 bugs whereas Keras did not localize any faults.
No abstract
No abstract
Internet of Things (IoT) has become a common buzzword nowadays in the Web. However, there is no search tool currently in place for discovering and learning about the different types of IoT elements. Hence, this paper presents a topical search engine for IoT. The motivation for a topical search engine comes from the relatively poor performance of generalpurpose search engines, which depend on the results of generic Web crawlers. The topical search engine is a system that learns the specialization from examples, and then explores the Web, guided by a relevance and popularity rating mechanism. The results show that the proposed topical search engine outperforms other general search engines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.