𝗔𝗡𝗡 𝗮𝗻𝗱 𝗖𝗡𝗡 𝗳𝗿𝗼𝗺 𝘀𝗰𝗿𝗮𝘁𝗰𝗵 | 𝗡𝗼 𝗳𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸𝘀, 𝗷𝘂𝘀𝘁 𝗽𝘂𝗿𝗲 𝗡𝘂𝗺𝗽𝘆
tftensor is a tensor library implemented in Rust. It offers tensor operations, automatic differentiation, and supports basic neural network training functionalities.
A collection of notebooks from my applied AI minor, featuring projects in machine learning, deep learning, and a neural network built from scratch.
A scratch-built NumPy implementation of a Fully Connected Neural Network, with a sequential model API, a variety of layers (Linear, ReLU, BatchNorm), loss functions (MSE, SoftmaxCrossEntropy), and a robust training `Solver` to create and train multi-layer perceptrons for both classification and regression.
A microscope for informed training of multi-layer perceptron, diagnosing training issues at granular level and accelerating learning and rapid prototyping.
A simple NumPy-based deep learning framework. Create and train neural networks easily, experiment with backpropagation, optimization, and explore the code to grasp the inner workings.
Mini-library that implements a simple version of a feedforward neural network (FNN) and convolutional neural network (CNN) from scratch using Python and PyTorch
Add a description, image, and links to the nn-from-scratch topic page so that developers can more easily learn about it.
To associate your repository with the nn-from-scratch topic, visit your repo's landing page and select "manage topics."