33K-Star GitHub Repo ML-From-Scratch Rebuilds ML Algorithms in Pure Python
techNmak · x · 2026-10-23
ML-From-Scratch, a GitHub repo by Erik Linder-Noren with 33K stars, reimplements classic machine learning algorithms in readable Python — prioritizing understanding over speed.
Coverage includes:
- Linear/logistic regression, decision trees, random forests, gradient boosting, XGBoost, SVMs
- Unsupervised methods: K-means, DBSCAN, PCA, Gaussian mixtures
- Neural networks, CNNs, and RNNs with full layer implementations (conv, pooling, batch norm, dropout)
- GANs and Deep Q-learning on CartPole
The neural network code is especially useful for developers who want to see what high-level libraries hide under the hood.
More from Research
- FreshStack retrieval leaderboard revamped, adds Cohere Embed v5 and EmbeddingGemma2 — beirmug · 2026-10-23
- Jakob Kather at ESMO: LLMs and AI agents in oncology, from single-task models to autonomy — jnkath · 2026-10-23
- Quantizing a 9B model: 70% of damage sits in the first 8 layers, and perplexity hides the tail — DinnerPrestigious953 · 2026-10-23
- GenReasoning team reflects on six-month grind: lean startup, zero paid promotion — rosstaylor90 · 2026-10-23
- Dev ports Anthropic's RISC-V formal verification model from Rocq to Lean — xennygrimmato_ · 2026-10-23
- THU-KEG Releases RIDAR to Detect and Intervene in Research Agent Integrity Violations — THU-KEG · 2026-10-23