 |
VOOZH | about |
A complete neural network built entirely in x86 assembly language that learns to recognize handwritten digits from the MNIST dataset. No frameworks, no high-level languages - just pure assembly - ~5.3× faster than NumPy
Data science teaching materials
A neural network library written from scratch in Rust along with a web-based application for building + training neural networks + visualizing their outputs
Detailed python notes & code for lectures and exercises of Andrej Karpathy's course "Neural Networks: Zero to Hero." The course is focused on building neural networks from scratch.
🤖 A TypeScript version of karpathy/micrograd — a tiny scalar-valued autograd engine and a neural net on top of it
An Open Convolutional Neural Network Framework in C++ From Scratch
Neural Networks from Scratch in Python crafted for utilization as teaching resources in graduate courses (Deep Learning, Deep Learning for Computer Vision) delivered by Minh-Chien Trinh at Jeonbuk National University.
Deep learning library in python from scratch
Unsupervised Deep Learning-based Pansharpening with Jointly-Enhanced Spectral and Spatial Fidelity
A step-by-step walkthrough of the inner workings of a simple neural network. The goal is to demystify the calculations behind neural networks by breaking them down into understandable components, including forward propagation, backpropagation, gradient calculations, and parameter updates.
Learn machine learning the hard way
My first ML sandbox
Implementation of feedforward-backpropagated Neural Network from Scratch
deep learning from scratch. uses numpy/cupy, trains in GPU, follows pytorch API
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.
Neural Networks Fundamentals with Python – implementing neural networks from scratch
Lightweight, easy to use, micro neural network framework written in Rust w/ no python dependencies
Let's build Neural Networks from scratch.
Matrix-Vector Library Designed for Neural Network Construction. cuda (gpu) support, openmp (multithreaded cpu) support, partial support of BLAS, expression template based implementation PTX code generation identical to hand written kernels, and support for auto-differentiation
Neural nets for high accuracy multivariable nonlinear regression.
Add a description, image, and links to the neural-networks-from-scratch topic page so that developers can more easily learn about it.
To associate your repository with the neural-networks-from-scratch topic, visit your repo's landing page and select "manage topics."