Neural Networks From Scratch Python Packages

melpy

A NumPy-based deep learning library for building neural networks. It features an automatic differentiation engine and supports training architectures like LSTM, CNN, and FNN.

neural-dsl

A causal inference engine for deep learning training that provides structured explanations of neural network training failures. Understand why your model failed during training through semantic analysis and abductive reasoning, not raw tensor inspection.

neuraldbg

A causal inference engine for deep learning training that provides structured explanations of neural network training failures. Understand why your model failed during training through semantic analysis and abductive reasoning, not raw tensor inspection.

nn-without-frameworks

Let's build Neural Networks from scratch.

aeronet-learn

AeroNet is an educational neural network library. It is written entirely using python, numpy, and scipy.

tortto

A PyTorch style machine learning framework written in NumPy with GPU acceleration from CuPy.