Dropout Based

Dropout-based Bayesian neural networks (BNNs) are being actively researched to improve the reliability and trustworthiness of AI systems by providing robust uncertainty quantification. Current efforts focus on optimizing dropout strategies, including exploring heterogeneous dropout configurations and multi-exit architectures, often within the context of hardware acceleration, particularly using FPGAs and spintronic computation-in-memory architectures to improve energy efficiency and performance. This research is significant because reliable uncertainty estimation is crucial for deploying AI in safety-critical applications, such as autonomous driving and medical diagnosis, where confidence in predictions is paramount.

Papers

June 23, 2024

Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA
Zehuan Zhang, Hongxiang Fan, Hao Mark Chen, Lukasz Dudziak, Wayne Luk
Field Programmable Gate Array Uncertainty Prediction Dropout Regularization Inference Based Adaptive Dropout Dropout Based

June 20, 2024

Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA
Hao Mark Chen, Liam Castelli, Martin Ferianc, Hongyu Zhou, Shuanglong Liu, Wayne Luk, Hongxiang Fan
Bayesian Neural Network Field Programmable Gate Array Multi Exit Bayes Net Dropout Based

January 9, 2024

Testing Spintronics Implemented Monte Carlo Dropout-Based Bayesian Neural Networks
Soyed Tuhin Ahmed, Michael Hefenbrock, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Bayesian Neural Network Monte Carlo Bayes Net Dropout Based

November 27, 2023

Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale
Soyed Tuhin Ahmed, Kamal Danouchi, Michael Hefenbrock, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Deep Neural Network High Uncertainty Anticipation Bayesian Neural Network Scalable Bayesian Dropout Based

June 16, 2023

Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation
Soyed Tuhin Ahmed, Kamal Danouchi, Michael Hefenbrock, Guillaume Prenat, Lorena Anghel, Mehdi B. Tahoori
Bayesian Neural Network Spatial Domain Unmatched Spatial Support Dropout Based

February 18, 2022

Out of Distribution Data Detection Using Dropout Bayesian Neural Networks
Andre T. Nguyen, Fred Lu, Gary Lopez Munoz, Edward Raff, Charles Nicholas, James Holt
Image Classification Distribution Detection Jina Embeddings Bayesian Neural Network Distribution Data Dropout Based

Dropout Based

Papers

Hardware-Aware Neural Dropout Search for Reliable Uncertainty Prediction on FPGA

Enhancing Dropout-based Bayesian Neural Networks with Multi-Exit on FPGA

Testing Spintronics Implemented Monte Carlo Dropout-Based Bayesian Neural Networks

Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale

Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation

Out of Distribution Data Detection Using Dropout Bayesian Neural Networks