mlp

Introduction to neural networks, with the implementation of a multilayer perceptron.

If you want to learn more about the way deep learning framework work.

Install

uv venv --python 3.12 .venv && uv pip install -e .

Training

uv run python examples/train_mlp.py

this will also save plot about the training data.

Inference

uv run python examples/inference_mlp.py

Load weight from training and perform inference on unseen data.

Other commands you can use, run a python server of the directory and view images in your browser for examples.

ToDo

• split train and prediction program
• refacto loss function
• implement SGD

my intuition is that giving 80% of the dataset in one pass of our model will make it learn so fast. it does not need to reajust much its weight.