gradient-free

Official implementation of Score-CAM in PyTorch

My optimization(With and Without gradient) library

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

Continuous domain Particle Swarm Optimization (PSO) with inertia weight decay and cognitive/social acceleration.

Continuous domain Particle Swarm Optimization (PSO) with inertia weight decay and cognitive/social acceleration.

Your language model forgets everything. Sillage gives it a 4 MB memory that persists across sessions, no gradients, no fine-tuning, no growing index. Beats an unbounded kNN-LM at 1/13 the storage (perplexity 31 → 17). CPU-only, fully reproducible, four preprints with Zenodo DOIs.

Fast runtime for Random Optimization at scale.

Similarity Differences and Uniqueness Explainable AI method

Tensorflow Optimizer using the SPSA method

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.

ADMM approach to train neural networks without gradient.

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

VRAXION public SDK and boundary docs for the private engine.

A Julia implementation of Simultaneous Perturbation Stochastic Approximation

Drift-Bounded Spectral Updates for Deep Local Learning

Gradient-free RL for LunarLander-v3 with population search, zeroth-order optimization, JAX, and parallel runs.

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

Gradient-free neural network optimisation: PSO vs Adam vs SGD — from-scratch NumPy, 29-test suite, CI/CD

Deep neural network trained with Particle Swarm Optimization (gradient-free), with the dnnpso package and benchmarks