An OS which is all about learning!
-
Updated
Jul 18, 2026 - Rust
#
from-scratch-implementation
Here are 27 public repositories matching this topic...
Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.
python education data-science machine-learning roadmap deep-learning neural-network scikit-learn machine-learning-algorithms ml pytorch artificial-intelligence xgboost-algorithm from-scratch-in-python from-scratch-implementation from-scratch-ml
-
Updated
Jul 19, 2026 - Jupyter Notebook
A from-scratch AlphaFold2 in PyTorch designed to make one of the most important and complex ML architectures readable, hackable, and ablatable.
structural-biology computational-biology geometric-deep-learning protein-structure-prediction pytorch-implementation alphafold2 evoformer protein-folding-prediction from-scratch-implementation invariant-point-attention
-
Updated
Jul 5, 2026 - Python
A from-scratch implementation of a feedforward neural network in C# (.NET 8) without using any machine learning frameworks.
machine-learning dotnet brain turkey deeplearning-demo neural-networks-from-scratch neural-network-design from-scratch-neural-network from-scratch-implementation
-
Updated
Nov 19, 2025 - C#
Educational, from-scratch implementation of a LLaMA-style LLM using PyTorch to explore Transformer architecture fundamentals.
nlp machine-learning natural-language-processing research deep-learning transformers pytorch neural-networks educational llama language-model from-scratch self-attention llm transformer-model model-implementation from-scratch-implementation
-
Updated
Jul 27, 2025 - Jupyter Notebook
A convolutional neural network (CNN) built from scratch using only NumPy to classify handwritten digits from the MNIST dataset.
python machine-learning deep-learning numpy cnn mnist convolutional-neural-networks gradient-descent from-scratch from-scratch-in-python from-scratch-neural-network from-scratch-implementation
-
Updated
Jul 3, 2025 - Jupyter Notebook
A decoder-only Transformer built from scratch using CuPy only — no PyTorch, no autograd, no magic. Every forward pass, backward pass, and gradient derived and implemented by hand. Includes full training loop, Adam optimizer, LayerNorm, and causal self-attention on GPU.
deep-learning neural-network transformer gpt language-model backpropagation cupy llms from-scratch-implementation no-pytorch
-
Updated
Mar 30, 2026 - Python
From-scratch PyTorch implementations of transformer components, BPE, decoding strategies, manual backprop, and RL.
reinforcement-learning transformers pytorch deep-learning-algorithms deep-learning-tutorial llms bpe-tokenizer from-scratch-implementation
-
Updated
May 22, 2026 - Jupyter Notebook
"Learn Linear Regression: A Python implementation from scratch with dataset generation and visualization" as it's both informative and engaging.
-
Updated
Jun 14, 2026 - Jupyter Notebook
From-scratch C++17 LiDAR + camera perception — sector RANSAC, LiDAR-inertial SLAM, MOT, probabilistic traversability, CBF safety. 13 engineering deep-dives.
protobuf eigen perception lidar cpp17 slam autonomous-vehicles kalman-filter ros2 slam-algorithms nats-messaging robotics-perception event-streaming moving-object-tracking control-barrier-functions rellis-3d traversability-mapping traversability pub-sub-system from-scratch-implementation
-
Updated
May 18, 2026 - C++
Implementation of KNN and Gaussian Naive-Bayes algorithms to classify phishing URLs. Built from scratch and compared with scikit-learn versions.
machine-learning python-programming data-preprocessing k-nearest-neighbors gaussian-naive-bayes from-scratch-implementation
-
Updated
Dec 23, 2024 - Jupyter Notebook
Manual implementation of backpropagation on a custom computational graph with gradient checking. Benchmarks Vanilla SGD, Momentum, and Adam optimizers from first principles using NumPy.
deep-learning numpy neural-networks gradient-descent backpropagation adam-optimizer sgd-optimizer computational-graph from-scratch-implementation
-
Updated
Mar 17, 2026 - Jupyter Notebook
This project demonstrates how to build and train a feedforward neural network from scratch using only NumPy, without any high-level deep learning libraries like TensorFlow or PyTorch. The model is trained on the MNIST digit classification dataset and achieves competitive accuracy.
-
Updated
Apr 30, 2025 - Python
ML algorithms implemented from scratch in Python, with small projects for better understanding.
data-science machinelearning machinelearning-python machinelearningprojects machinelearningalgorithms from-scratch-in-python from-scratch-implementation machinelearningtutorial
-
Updated
Jun 26, 2026 - Jupyter Notebook
A minimalist, CUDA-native deep learning library featuring a custom autograd system and a PyTorch-inspired API, built to explore framework internals and GPU-accelerated computing.
-
Updated
May 26, 2026 - C++
MapReduce POC Implementation
-
Updated
Jan 1, 2025 - Python
From-scratch implementation of binary Logistic Regression using NumPy, with vectorized cost computation, gradient calculation, and batch gradient descent optimization.
python numpy logistic-regression matplotlib gradient-descent cost-function sigmoid-function from-scratch-implementation
-
Updated
Apr 15, 2026 - Jupyter Notebook
A curl implementation written in python3.
cli curl python3 implementation no-dependencies from-scratch cli-tool from-scratch-in-python from-scratch-implementation
-
Updated
May 24, 2026 - Python
Improve this page
Add a description, image, and links to the from-scratch-implementation topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the from-scratch-implementation topic, visit your repo's landing page and select "manage topics."