Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation
Recently, machine learning systems have gained prominence in real-time, critical decision-making domains, such as autonomous driving and industrial automation. Their implementations should avoid overconfident predictions through uncertainty estimation. Bayesian Neural Networks (BayNNs) are principled methods for estimating predictive uncertainty. However, their computational costs and power consumption hinder their widespread deployment in edge AI. Utilizing Dropout as an approximation of the posterior distribution, binarizing the parameters of BayNNs, and further to that implementing them in spintronics-based computation-in-memory (CiM) hardware arrays provide can be a viable solution. However, designing hardware Dropout modules for convolutional neural network (CNN) topologies is challenging and expensive, as they may require numerous Dropout modules and need to use spatial information to drop certain elements. In this paper, we introduce MC-SpatialDropout, a spatial dropout-based approximate BayNNs with spintronics emerging devices. Our method utilizes the inherent stochasticity of spintronic devices for efficient implementation of the spatial dropout module compared to existing implementations. Furthermore, the number of dropout modules per network layer is reduced by a factor of $9\times$ and energy consumption by a factor of $94.11\times$, while still achieving comparable predictive performance and uncertainty estimates compared to related works.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingDecision MakingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Bayesian Deep Learning for Affordance Segmentation in images
Affordances are a fundamental concept in robotics since they relate available actions for an agent depending on its sensory-motor capabilities and the environment. We present a novel Bayesian deep network to detect affor…
AttributeDeep LearningInstance SegmentationSemantic SegmentationA Bayesian approach for estimation of weight matrices in spatial autoregressive models
We develop a Bayesian approach to estimate weight matrices in spatial autoregressive (or spatial lag) models. Datasets in regional economic literature are typically characterized by a limited number of time periods T rel…
Variance-Penalized MC-Dropout as a Learned Smoothing Prior for Brain Tumour Segmentation
Brain tumor segmentation is essential for diagnosis and treatment planning, yet many CNN and U-Net based approaches produce noisy boundaries in regions of tumor infiltration. We introduce UAMSA-UNet, an Uncertainty-Aware…
Computational EfficiencyBrain Tumor SegmentationBayesian Graph Convolutional Network for Traffic Prediction
Recently, adaptive graph convolutional network based traffic prediction methods, learning a latent graph structure from traffic data via various attention-based mechanisms, have achieved impressive performance. However, …
PredictionTraffic PredictionEnhancing Lithological Mapping with Spatially Constrained Bayesian Network (SCB-Net): An Approach for Field Data-Constrained Predictions with Uncertainty Evaluation
Geological maps are an extremely valuable source of information for the Earth sciences. They provide insights into mineral exploration, vulnerability to natural hazards, and many other applications. These maps are create…