GitHub

Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction

In autonomous driving, understanding the 3D world over time is critical. Yet, most vision-based 3D Occupancy (VisionOcc) methods only scratch the surface of temporal fusion, focusing on simple ...
IEEE

Gradient Descent Algorithm Based on Extended State Observer for Loss Minimization of Ultralocal Model Predictive Controlled PMSM Drives

Abstract: Hybrid loss minimization algorithms in electrical drives combine the benefits of search-based and model-based approaches to deliver fast and robust dynamic responses. This article presents a ...
IEEE

Fixed Versus Backtracking Step Sizes in Gradient Descent and Nesterov Acceleration

Abstract: Optimization methods are fundamental to machine learning, with Gradient Descent (GD) being one of the most widely used first-order algorithm. However, GD's convergence can be slow for ...