Simon Fraser University

Finite Difference Approximations of Derivatives

First-order derivatives: n additional function calls are needed. Second-order derivatives based on gradient calls, when the "grd" module is specified (Dennis and Schnabel 1983): n additional gradient ...
IEEE

Pedestrian Dead Reckoning and Ultrawideband Fusion Positioning Algorithm Based on Adaptive Gradient Descent

Abstract: In order to address the challenges of unknown initial positions and accumulated long-distance positioning errors in pedestrian dead reckoning (PDR), as well as significant ranging errors ...
IEEE

Novel Adversarial Attack Method Based on Adaptive Gradient Algorithm

Abstract: Although current adversarial attack techniques have made significant progress in the field of deep learning, they mainly focus on adding subtle perturbations to deep learning models that are ...
GitHub

Interactive visualization of gradient descent optimization algorithms. Demonstrates learning dynamics, convergence behavior, and parameter updates for machine learning education.

Multiple learning rate comparisons (0.01, 0.05, 0.1, 0.5, 1.0) Activation function analysis Training vs testing accuracy evaluation Regularization techniques (L2) ...