Search Results for author:
Found 9 papers, 2 papers with code
Tiny Deep Ensemble: Uncertainty Estimation in Edge AI Accelerators via Ensembling Normalization Layers with Shared Weights
Therefore, latency and memory overhead are reduced by a factor of up to $\sim M\times$.
Embedding Hardware Approximations in Discrete Genetic-based Training for Printed MLPs
Due to the discrete nature of hardware approximation, we propose and implement a genetic-based, approximate, hardware-aware training approach specifically designed for printed MLPs.
Testing Spintronics Implemented Monte Carlo Dropout-Based Bayesian Neural Networks
Bayesian Neural Networks (BayNNs) can inherently estimate predictive uncertainty, facilitating informed decision-making.
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.
Improving Deep Learning Optimization through Constrained Parameter Regularization
Unlike the uniform application of a single penalty, CPR enforces an upper bound on a statistical measure, such as the L2-norm, of individual parameter matrices.
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.
Universal Distributional Decision-based Black-box Adversarial Attack with Reinforcement Learning
In this work, we propose a pixel-wise decision-based attack algorithm that finds a distribution of adversarial perturbation through a reinforcement learning algorithm.
McXai: Local model-agnostic explanation as two games
Our method leverages Monte Carlo tree search and models the process of generating explanations as two games.
Automatic Remaining Useful Life Estimation Framework with Embedded Convolutional LSTM as the Backbone
An essential task in predictive maintenance is the prediction of the Remaining Useful Life (RUL) through the analysis of multivariate time series.
