Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2406.14593 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916298597859328 |
|---|---|
| author | Chen, Hao Mark Castelli, Liam Ferianc, Martin Zhou, Hongyu Liu, Shuanglong Luk, Wayne Fan, Hongxiang |
| author_facet | Chen, Hao Mark Castelli, Liam Ferianc, Martin Zhou, Hongyu Liu, Shuanglong Luk, Wayne Fan, Hongxiang |
| contents | Reliable uncertainty estimation plays a crucial role in various safety-critical applications such as medical diagnosis and autonomous driving. In recent years, Bayesian neural networks (BayesNNs) have gained substantial research and industrial interests due to their capability to make accurate predictions with reliable uncertainty estimation. However, the algorithmic complexity and the resulting hardware performance of BayesNNs hinder their adoption in real-life applications. To bridge this gap, this paper proposes an algorithm and hardware co-design framework that can generate field-programmable gate array (FPGA)-based accelerators for efficient BayesNNs. At the algorithm level, we propose novel multi-exit dropout-based BayesNNs with reduced computational and memory overheads while achieving high accuracy and quality of uncertainty estimation. At the hardware level, this paper introduces a transformation framework that can generate FPGA-based accelerators for the proposed efficient multi-exit BayesNNs. Several optimization techniques such as the mix of spatial and temporal mappings are introduced to reduce resource consumption and improve the overall hardware performance. Comprehensive experiments demonstrate that our approach can achieve higher energy efficiency compared to CPU, GPU, and other state-of-the-art hardware implementations. To support the future development of this research, we have open-sourced our code at: https://github.com/os-hxfan/MCME_FPGA_Acc.git |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14593 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA Chen, Hao Mark Castelli, Liam Ferianc, Martin Zhou, Hongyu Liu, Shuanglong Luk, Wayne Fan, Hongxiang Machine Learning Reliable uncertainty estimation plays a crucial role in various safety-critical applications such as medical diagnosis and autonomous driving. In recent years, Bayesian neural networks (BayesNNs) have gained substantial research and industrial interests due to their capability to make accurate predictions with reliable uncertainty estimation. However, the algorithmic complexity and the resulting hardware performance of BayesNNs hinder their adoption in real-life applications. To bridge this gap, this paper proposes an algorithm and hardware co-design framework that can generate field-programmable gate array (FPGA)-based accelerators for efficient BayesNNs. At the algorithm level, we propose novel multi-exit dropout-based BayesNNs with reduced computational and memory overheads while achieving high accuracy and quality of uncertainty estimation. At the hardware level, this paper introduces a transformation framework that can generate FPGA-based accelerators for the proposed efficient multi-exit BayesNNs. Several optimization techniques such as the mix of spatial and temporal mappings are introduced to reduce resource consumption and improve the overall hardware performance. Comprehensive experiments demonstrate that our approach can achieve higher energy efficiency compared to CPU, GPU, and other state-of-the-art hardware implementations. To support the future development of this research, we have open-sourced our code at: https://github.com/os-hxfan/MCME_FPGA_Acc.git |
| title | Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.14593 |