When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA

Fan, Hongxiang, Chen, Hao, Castelli, Liam, Que, Zhiqiang, Li, He, Long, Kenneth, Luk, Wayne

arXiv.org Artificial Intelligence 

Bayesian Neural Networks (BayesNNs) have demonstrated their capability of providing calibrated prediction for safety-critical applications such as medical imaging and autonomous driving. However, the high algorithmic complexity and the poor hardware performance of BayesNNs hinder their deployment in real-life applications. To bridge this gap, this paper proposes a novel multi-exit Monte-Carlo Dropout (MCD)-based BayesNN that achieves well-calibrated predictions with low algorithmic complexity. To further reduce the barrier to adopting BayesNNs, we propose a transformation framework that can generate FPGA-based accelerators for multi-exit MCD-based BayesNNs. Several novel optimization techniques are introduced to improve hardware performance. Our experiments demonstrate that our auto-generated accelerator achieves higher energy efficiency than CPU, GPU, and other state-of-the-art hardware implementations.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found