Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 4 of 4
Full-Text Articles in Engineering
Cooperative Deep Q -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan
Cooperative Deep Q -Learning Framework For Environments Providing Image Feedback, Krishnan Raghavan, Vignesh Narayanan, Sarangapani Jagannathan
Publications
In this article, we address two key challenges in deep reinforcement learning (DRL) setting, sample inefficiency, and slow learning, with a dual-neural network (NN)-driven learning approach. In the proposed approach, we use two deep NNs with independent initialization to robustly approximate the action-value function in the presence of image inputs. In particular, we develop a temporal difference (TD) error-driven learning (EDL) approach, where we introduce a set of linear transformations of the TD error to directly update the parameters of each layer in the deep NN. We demonstrate theoretically that the cost minimized by the EDL regime is an approximation …
Efficient, Low-Cost Bridge Cracking Detection And Quantification Using Deep-Learning And Uav Images, Chao Sun, Xiangyu Meng, Joshua O. Ogbebor, Shaopan Guo
Efficient, Low-Cost Bridge Cracking Detection And Quantification Using Deep-Learning And Uav Images, Chao Sun, Xiangyu Meng, Joshua O. Ogbebor, Shaopan Guo
Publications
Many bridges in the State of Louisiana and the United States are working under serious degradation conditions where cracks on bridges threaten structural integrity and public security. To ensure structural integrity and public security, it is required that bridges in the US be inspected and rated every two years. Currently, this biannual assessment is largely implemented using manual visual inspection methods, which is slow and costly. In addition, it is challenging for workers to detect cracks in regions that are hard to reach, e.g., the top part of the bridge tower, cables, mid-span of the bridge girders, and decks. This …
Knowledge Infused Learning (K-Il): Towards Deep Incorporation Of Knowledge In Deep Learning, Ugur Kursuncu, Manas Gaur, Amit Sheth
Knowledge Infused Learning (K-Il): Towards Deep Incorporation Of Knowledge In Deep Learning, Ugur Kursuncu, Manas Gaur, Amit Sheth
Publications
Learning the underlying patterns in data goes beyondinstance-based generalization to external knowledge repre-sented in structured graphs or networks. Deep learning thatprimarily constitutes neural computing stream in AI hasshown significant advances in probabilistically learning la-tent patterns using a multi-layered network of computationalnodes (i.e., neurons/hidden units). Structured knowledge thatunderlies symbolic computing approaches and often supportsreasoning, has also seen significant growth in recent years,in the form of broad-based (e.g., DBPedia, Yago) and do-main, industry or application specific knowledge graphs. Acommon substrate with careful integration of the two willraise opportunities to develop neuro-symbolic learning ap-proaches for AI, where conceptual and probabilistic repre-sentations are combined. …
Coverage Guided Differential Adversarial Testing Of Deep Learning Systems, Jianmin Guo, Houbing Song, Yue Zhao, Yu Jiang
Coverage Guided Differential Adversarial Testing Of Deep Learning Systems, Jianmin Guo, Houbing Song, Yue Zhao, Yu Jiang
Publications
Deep learning is increasingly applied to safety-critical application domains such as autonomous cars and medical devices. It is of significant importance to ensure their reliability and robustness. In this paper, we propose DLFuzz, the coverage guided differential adversarial testing framework to guide deep learing systems exposing incorrect behaviors. DLFuzz keeps minutely mutating the input to maximize the neuron coverage and the prediction difference between the original input and the mutated input, without manual labeling effort or cross-referencing oracles from other systems with the same functionality. We also design multiple novel strategies for neuron selection to improve the neuron coverage. The …