deep-learning-from-scratch

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

🔬 The most atomic GPT-2 implementation in 265 lines of pure Python & CUDA. A bilingual "Rosetta Stone" for understanding LLM internals from scratch. No dependencies, just math and kernels.

Deep Learning Framework only using numpy: Linear, Convolution, Flatten, Max and Mean Pooling layers, activation functions, Softmax, MSE and Cross Entropy. Useful functions: train, save an load a model to deploy it, get nb of parameters, draw learning curves

Single-layer Perceptron (Logistic Regression) binary classifier in Python, powered by a high-performance C++20 matrix engine (matrixlib) via Pybind11.

📖 ⟪밑바닥부터 시작하는 딥러닝2⟫ 스터디 기록 저장소

Deep learning from scratch in pure NumPy — tensors, layers, losses, and optimizers with hand-written backward passes and no autograd. A learning project with math notes for every algorithm.

A zero-dependency Dense MLP neural network built completely from scratch in NumPy, featuring custom activation overflow clipping and modular data pipelines.

"A from-scratch implementation of a modern Large Language Model (LLaMA architecture). Features full backpropagation calculus in pure NumPy, followed by a GPU-accelerated PyTorch training loop."

A lightweight, deep learning library written in pure Python

A coding exercises with numpy and pytest for Deep Learning From Scratch

A Python project implementing a neural network framework from scratch using NumPy. Includes fully connected (Dense) layers, ReLU and Sigmoid activations, a simple SGD optimizer, and a minimal training loop. Designed for hands-on learning of neural network fundamentals without relying on any deep learning frameworks

从零实现的自动微分引擎(200 行, 批量节点 + 广播 + 拓扑反向传播), 用来训练 MLP 并实时可视化决策边界与损失曲线。41 项无依赖测试含数值梯度校验。

How neural networks learn from first principles — linear algebra, backpropagation, gradient checking, and gradient descent.

밑바닥부터 시작하는 딥러닝 스터디 요약 저장소 (HW)

Notebook edukatif yang membangun intuisi bahwa neural network adalah tumpukan operasi matriks, dan bahwa backpropagation adalah aplikasi chain rule.

Deep Learning from scratch: mathematical derivations, manual forward/backward implementations of MLPs, CNNs, RNNs, LSTMs and GRUs, followed by practical PyTorch implementations of modern neural network architectures. Written in Python & PyTorch.

A 1,756-parameter single-image super-resolution model built from scratch in pure NumPy — hand-written backprop, Adam, and frequency-band modulation (AdaFM). Trains on one CPU core in minutes; beats bicubic on Set14 and Urban100.

Réseau de neurones implémenté en NumPy pour la reconnaissance de chiffres manuscrits (MNIST)

A from-scratch neural network built in NumPy to classify handwritten digits (MNIST), demonstrating forward propagation, backpropagation, and gradient descent without deep learning frameworks.

Decoder-only transformer written from scratch in C++17, using Scalpel as its vocabulary layer.