fisher

PyTorchRelevancePropagation. A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.

TicTacToe. Environment equipped with reinforcement learning algorithms to train agents to play tic-tac-toe.

CppMultilayerPerceptron. A simple class for fully connected neural networks.

LayerwiseRelevancePropagation. A basic implementation of the Layer-wise Relevance Propagation algorithm in Tensorflow.

NeuralAnnealing. Simulated annealing for neural networks with JAX.

DroneRacing. A simple learning environment with drones for evolution-inspired optimization.

RocketLander. A simple framework equipped with optimization algorithms, such as reinforcement learning, evolution strategies, genetic optimization, and simulated annealing, to enable an orbital rocket booster to land autonomously.

RealTimeRelevancePropagation. An implementation for real time layer-wise relevance propagation using OpenCV and Tensorflow.

NeuralGrid. A grid-based neural network architecture.

VanillaTreeSPH. A simple smoothed-particle hydrodynamics code that uses a tree algorithm to find neighbour particles.

PyDualNumber. Basic implementation of dual numbers in Python.

PyAutograd. Minimal, scalar-valued, dependency-free Python library for reverse-mode automatic differentiation.

MinMixer. A minimal MLP-Mixer architecture for image classification.

MathLang. Investigate the capabilities of neural networks to process mathematical expressions.

NeuroEvolution. A hybrid optimization algorithm that combines gradient descent for network parameter optimization and an evolutionary algorithm for network topology optimization.

GeneticWheels. Genetic optimization algorithm for the evolution of wheels.

GeneticNeuralNetworkTraining. A Python implementation of a genetic optimizer for fully connected neural networks