Binary Bayesian Neural Networks for Efficient Uncertainty Estimation Leveraging Inherent Stochasticity of Spintronic Devices - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Binary Bayesian Neural Networks for Efficient Uncertainty Estimation Leveraging Inherent Stochasticity of Spintronic Devices

Soyed Tuhin
  • Fonction : Auteur
Christopher Münch
Lorena Anghel
Mehdi B Tahoori
Bayesian Neural
  • Fonction : Auteur

Résumé

In the age of automation, machine learning systems for real-time critical decisions in various domains such as autonomous driving are at an all-time high. Predictive uncertainty allows a machine learning system to make more insightful decisions by avoiding blind predictions. Algorithmically, Bayesian neural networks (BayNNs) based on dropout are principled methods for estimating predictive uncertainty in a machine learning application. However, the computational cost and power consumption make the use of BayNNs on embedded hardware unattractive. Hardware accelerators with emerging non-volatile resistive memories (NVMs) such as Magnetic Tunnel Junction (MTJ) in conjunction with quantized models are an interesting option for efficient implementations of such a system. Binary BayNNs are a desirable alternative that can provide predictive uncertainty efficiently by combining the benefits of quantization and hardware acceleration. In this paper, propose for the first time the binary bayesian neural network (BayBNN) using dropout-based approximation, and we leverage the inherent randomness of spin- tronic devices for in-memory Bayesian inference. Our proposed method can detect up-to 100% of the out-of-distribution data, improve inference accuracy by 15% for corrupted data, and ∼ 2% for in-distribution data.

Dates et versions

hal-04054228 , version 1 (31-03-2023)

Identifiants

Citer

Soyed Tuhin, Kamal Danouchi, Christopher Münch, Guillaume Prenat, Lorena Anghel, et al.. Binary Bayesian Neural Networks for Efficient Uncertainty Estimation Leveraging Inherent Stochasticity of Spintronic Devices. 17th ACM International Symposium on Nanoscale Architectures, Association for Computing machinery, Dec 2022, Virtual conference, United States. ⟨10.1145/3565478.3572536⟩. ⟨hal-04054228⟩
16 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More