Journal
2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)
Volume -, Issue -, Pages -Publisher
IEEE
DOI: 10.1109/IJCNN52387.2021.9534143
Keywords
Deep Learning; Hardware Implemented Neural Network; Analog Device; Additive White Gaussian Noise
Categories
Funding
- U.S. Dept. of Navy [N00014-17-1-3062]
- U.S. Office of the Under Secretary of Defense for Research and Engineering (OUSD(RE)) [FA8750-15-2-0119]
Ask authors/readers for more resources
Deeper models and models with more redundancy in design, such as VGG, are generally more robust to noise in analog devices. Additionally, performance is affected by factors such as the design philosophy of the model, detailed model structure, machine learning task, and datasets.
Analog hardware implemented deep learning models are promising for computation and energy constrained systems such as edge computing devices. However, the analog nature of the device and the many associated noise sources will cause changes to the value of the weights in the trained deep learning models deployed on such devices. In this study, systematic evaluation of the inference performance of trained popular deep learning models for image classification deployed on analog devices has been carried out, where additive white Gaussian noise has been added to the weights of the trained models during inference. It is observed that deeper models and models with more redundancy in design, such as VGG, are more robust to the noise in general. Also, it is observed that the performance is affected by the design philosophy of the model, the detailed structure of the model, the exact machine learning task, as well as the datasets.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available