Name
Title | ||
|---|---|---|
ASBNN: Acceleration of Bayesian Convolutional Neural Networks by Algorithm-hardware Co-design |
Abstract | ||
|---|---|---|
Bayesian Convolutional Neural Networks (BCNNs) have been proposed to address the problem of model uncertainty in conventional neural networks. By treating weights as distributions rather than deterministic values, BCNNs mitigate the problem of overfitting, training with a small amount of data, and uncertainty evaluations. However, computing the distributions of BCNN outputs is time- and energy-con... |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/ASAP52443.2021.00041 | 2021 IEEE 32nd International Conference on Application-specific Systems, Architectures and Processors (ASAP) |
Keywords | DocType | ISSN |
Uncertainty,Neural networks,Approximation algorithms,Hardware,Energy efficiency,Classification algorithms,Computational efficiency | Conference | 2160-0511 |
ISBN | Citations | PageRank |
978-1-6654-2701-2 | 0 | 0.34 |
References | Authors | |
0 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yoshiki Fujiwara | 1 | 0 | 0.34 |
| Shinya Takamaeda-Yamazaki | 2 | 65 | 16.83 |