kaifishr Goto Github PK

adaptivelearningrate

An adaptive learning rate method for gradient descent optimization algorithms.

chatmixer

A PyTorch implementation of MLP-Mixer and ConvMixer architectures for character-level natural language processing.

cppmultilayerperceptron

A simple class for fully connected neural networks.

geneticneuralnetworktraining

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

geneticwheels

Genetic optimization algorithm for the evolution of wheels.

kaifishr.github.io

My corner of the internet.

layerwiserelevancepropagation

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

littleshakespeare

A minimal character-level language model using a Recurrent Neural Network in Python + Tensorflow

mathlang

Investigate the capabilities of neural networks to process mathematical expressions.

minmixer

A minimal MLP-Mixer architecture for image classification.

netlab

A minimal development framework for rapid prototyping in PyTorch.

neuralannealing

Simulated annealing for neural networks with JAX.

neuralgrid

A grid-based neural network architecture.

neuroevolution

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

numpymultilayerperceptron

A vanilla Numpy implementation of a Multilayer Perceptron

pyautograd

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

pydualnumber

Basic implementation of dual numbers in Python.

pytorchrelevancepropagation

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

randomdynamics

A small program inspired by cellular automata

realtimerelevancepropagation

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

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.

sciformer

Minimal multi-head self-attention transformer architecture with experimental features implemented in PyTorch.

signalnoisegradients

Noise adjusted gradients for batch stochastic gradient descent.

snake

A minimal environment equipped with reinforcement learning algorithms to train an agent to play Snake.

spacedrones

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

subnetworkactivationfunctions

An implementation of trainable activation functions represented by small fully connected neural networks.

tictactoe

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

vanillacollisionsimulation

vanillageneticclassifier

A vanilla genetic classifier

vanillatreesph

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