Files and links (1)
Published, Version of Record (VoR)CC BY V4.0, Open
Journal article
Built-In Functional Testing of Analog In-Memory Accelerators for Deep Neural Networks
Electronics (Basel), v 11(2592), p2592
01 Aug 2022
Featured in Collection : UN Sustainable Development Goals @ Drexel
Abstract
The paper develops a methodology for the online built-in self-testing of deep neural network (DNN) accelerators to validate the correct operation with respect to their functional specifications. The DNN of interest is realized in the hardware to perform in-memory computing using non-volatile memory cells as computational units. Assuming a functional fault model, we develop methods to generate pseudorandom and structured test patterns to detect hardware faults. We also develop a test-sequencing strategy that combines these different classes of tests to achieve high fault coverage. The testing methodology is applied to a broad class of DNNs trained to classify images from the MNIST, Fashion-MNIST, and CIFAR-10 datasets. The goal is to expose hardware faults which may lead to the incorrect classification of images. We achieve an average fault coverage of 94% for these different architectures, some of which are large and complex.
Metrics
Details
- Title
- Built-In Functional Testing of Analog In-Memory Accelerators for Deep Neural Networks
- Creators
- Abhishek Kumar Mishra - Drexel UniversityAnup Kumar Das - Drexel UniversityNagarajan Kandasamy - Drexel University
- Publication Details
- Electronics (Basel), v 11(2592), p2592
- Publisher
- MDPI AG
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Electrical and Computer Engineering
- Web of Science ID
- WOS:000845985800001
- Scopus ID
- 2-s2.0-85137380352
- Other Identifier
- 991019173849804721
UN Sustainable Development Goals (SDGs)
This publication has contributed to the advancement of the following goals:
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Web of Science research areas
- Computer Science, Information Systems
- Engineering, Electrical & Electronic
- Physics, Applied