Symbiotic Hybrid Neural Network Watchdog For Outlier Detection

Autor:	Bui, Justin, Marks II, Robert J.
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Electrical Engineering and Systems Science - Image and Video Processing
Zdroj:	17th International Conference on Machine Learning and Data Mining, MLDM 2021, New York, USA, July 18-22, 2021 Proceedings, Pages 171-181
Druh dokumentu:	Working Paper
Popis:	Neural networks are largely black boxes. A neural network trained to classify fruit may classify a picture of a giraffe as a banana. A neural network watchdog's job is to identify such inputs, allowing a classifier to disregard such data. We investigate whether the watchdog should be separate from the neural network or symbiotically attached. We present empirical evidence that the symbiotic watchdog performs better than when the neural networks are disjoint. Comment: 10 Pages, 25 References, 10 Figures, 5 Tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2103.00582 Zobrazit plný text záznamu View this record from Arxiv