Tensorflow Optimizer using the SPSA method

A Julia implementation of Simultaneous Perturbation Stochastic Approximation

This repo shows a MATLAB implementation of score-CAM (Wang et al., CVPR workshop, 2020). This method is the first gradient-free CAM-based visualization method for explaining CNN decision.

Similarity Differences and Uniqueness Explainable AI method

ADMM approach to train neural networks without gradient.

Official implementation of Score-CAM in PyTorch

Repository containing code to run Score-CAM algorithm available on https://arxiv.org/pdf/1910.01279v1.pdf.

Code for FLEX, a fast, adaptive and flexible model-based reinforcement learning exploration algorithm.

My optimization(With and Without gradient) library

Visualizing 3D ResNet for Medical Image Classification With Score-CAM

0th order optimizers, gradient chaining, random gradient approximation