MLGarden
a tool/toy to build and train simple neural networks visually. I made this tool to get some better intuition on how neural networks/backpropagation worked, but I'm really unsure what to do with it now, so I've put it up on github, and I wrote a little primer on backprop and neural networks to showcase it.
Open source
Reactions (1)
Similar products
by description similarity
Reimplementing PyTorch from scratch (MLP
github.comCNN) to learn the internals
I created a Neural Network from scratch
bell-boy.github.ioin scratch
Cellulose
cellulose.aia tool to improve inference performance of ML models
Watch a neural net learn to play Snake
ppo.gradexp.xyzIn browser PPO training demo, made possible by tinygrad: TinyJit -> WebGPU kernels.
A C++ implementation of a Multilayer Perceptron (MLP) neural network using Eigen, supporting multiple activation and loss functions, mini-batch gradient descent, and backpropagation for training.