Search Results for author:
Found 8 papers, 0 papers with code
Enhancing Reliability of Neural Networks at the Edge: Inverted Normalization with Stochastic Affine Transformations
Bayesian Neural Networks (BayNNs) naturally provide uncertainty in their predictions, making them a suitable choice in safety-critical applications.
Scalable and Efficient Methods for Uncertainty Estimation and Reduction in Deep Learning
Neural networks (NNs) can achieved high performance in various fields such as computer vision, and natural language processing.
NeuSpin: Design of a Reliable Edge Neuromorphic System Based on Spintronics for Green AI
Internet of Things (IoT) and smart wearable devices for personalized healthcare will require storing and computing ever-increasing amounts of data.
Testing Spintronics Implemented Monte Carlo Dropout-Based Bayesian Neural Networks
Bayesian Neural Networks (BayNNs) can inherently estimate predictive uncertainty, facilitating informed decision-making.
Concurrent Self-testing of Neural Networks Using Uncertainty Fingerprint
During the online operation, by matching the uncertainty fingerprint, we can concurrently self-test NNs with up to $100\%$ coverage with a low false positive rate while maintaining a similar performance of the primary task.
Scale-Dropout: Estimating Uncertainty in Deep Neural Networks Using Stochastic Scale
In this paper, we propose the Scale Dropout, a novel regularization technique for Binary Neural Networks (BNNs), and Monte Carlo-Scale Dropout (MC-Scale Dropout)-based BayNNs for efficient uncertainty estimation.
Spatial-SpinDrop: Spatial Dropout-based Binary Bayesian Neural Network with Spintronics Implementation
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.
One-Shot Online Testing of Deep Neural Networks Based on Distribution Shift Detection
Neural networks (NNs) are capable of learning complex patterns and relationships in data to make predictions with high accuracy, making them useful for various tasks.
