Сustom torch style machine learning framework with automatic differentiation implemented on numpy, allows build GANs, VAEs, etc.

deep learning from scratch. uses numpy/cupy, trains in GPU, follows pytorch API

A simple fully connected feed forward neural network written in python from scratch using numpy & optimized using numba. It is possible to have multiple hidden layers, change amount of neurons per layer & have a different activation function per layer.

Python3 implementation of the Unsupervised Deep Learning Algorithm, Restricted Boltzmann Machine.

Computer vision project that utilized openCV to detect a soccer ball and players in a livestream of a soccer game.

A proof of concept of a recursion doing stochastic gradient descent for a simple neural network. Done in Python3 with numpy

TCC do curso de Análise e Desenvolvimento de Sistemas - FATEC - A Utilização de Algoritmos Genéticos na Otimização de Problemas

Small NeuralNet-Framework implemented with NumPy (Convolution|TransposeConv|Linear)

Trained deep neural networks to predict and classify input image (MNISTDD) datasets with python.

CNN model for MNIST dataset implemented from scratch using NumPy

Dimag, Nepali for the brain is an object-oriented neural network framework developed by me using python3.

A simple homebrew neural network created for MTE 203.

Neural networks

This is to see how a kernel will convolve over an image and what will be its output after convolution

NumPy-based feed-forward neural network

Implementation of a simple neural network in numpy.

OmniNumPy is an experimental compatibility layer that sits on top of modern NumPy (≥2.0) and lets you run the same code across multiple array backends — NumPy, PyTorch, CuPy, and JAX — with minimal changes.

Neural Networks and training algorithms in Numpy, for learning purpose.