Workshops Archive

Classification and Protection of Critical Weights in CNNs

Workshop: Women in HPC: Diversifying the HPC Community and Engaging Male Allies

Authors: Anna Schmedding (College of William & Mary)

Abstract: Convolutional neural networks (CNNs) are being incorporated into many image-based tasks across a variety of domains. Some of these tasks are real-world safety critical tasks such as object detection and lane line detection for self-driving cars. These applications have strict safety requirements and must be able guarantee the reliable operation of the network. We propose a selective triplication of important parts of the network determined via weight pruning methodologies in order to maintain a reliable CNN in environments that may be resource-limited.

Website:

Back to Women in HPC: Diversifying the HPC Community and Engaging Male Allies Archive Listing

Back to Full Workshop Archive Listing