Showing 30 of 1,438 · Category: Machine Learning
A decision model that returns calibrated answers to yes/no, choice, score and multi-label questions.
Stanford CS336《从头构建大语言模型》2026 中配版：18 篇中文技术博客 + 19 篇「图-字幕」原始文稿，基于 video2blog-skill 整理。
Guía gratuita de IA generativa avanzada en español (311 págs.): Transformer, post-entrenamiento, inferencia, GPU, difusión, agentes, seguridad. Free advanced generative AI guide in Spanish. CC0.
A visual desktop editor for creating publication-ready scientific figures, with domain-specific libraries, real-time collaboration, and export to PDF, SVG, PNG, and LaTeX/TikZ.
Deterministic symbolic codes for embedding vectors. Byte-identical across CPUs and languages, content-addressed, diffable and verifiable. C core with Python, Rust, Go and TypeScript bindings.
Atom-JEPA: Joint-Embedding Predictive Architecture for 3D Atomistic Systems
🌳 Groot 1 — open typed-decision model. Calibrated choice/score/yes-no answers over 64k-token states, System One API compatible, with a pure Bend engine. Beats Jev on zero-shot Folha news (87.8% vs 85.8%) and typed decisions (75.3% vs 73.7%).
A repository for mathematics in machine learning, covering linear algebra, calculus, probability, and statistics through structured notes, practical examples, and Python implementations.
Fast local AI decisions inside your application. A shared library and C API built on laya.cpp that runs the Laya typed-decision model in-process: no server, no Python. Windows, Linux and macOS, x64 and ARM64, CPU or GPU. An open-source alternative to Jev
A reading path for computer vision engineering, from photon to production. Primary sources in dependency order, evidence-graded claims, and a runnable benchmark per section.
My Lookup-Transformer solution for Kaggle S6E8: public LB ROC AUC 0.97041. Adopted in a 14th-place solution; 11 verified Kaggle references.
From-scratch Mixture-of-Experts (MoE) language model and offline AI engine in pure Python & NumPy. Zero PyTorch. Zero GGUF.
Study synthetic wind forecasts, asymmetric offer decisions & reproducible revenue backtests through transparent lessons.
Interactive semantic map of all 9,110 accepted NeurIPS 2026 papers using SPECTER2, UMAP and HDBSCAN.
An Efficient Low-Resource Bootstrap for Topic Model Refinement in Zero-Shot Settings
JalSuraksha replaces static simulations with an authoritative, production-grade geospatial intelligence platform that aggregates live and scheduled groundwater, reservoir, rainfall, and water quality telemetry across India (India-WRIS, CGWB, CWC, IMD, CPCB, Open-Meteo).
A config-driven library for reinforcement-learning fine-tuning. One YAML file trains with GRPO, DPO, or SFT on a local GPU, SageMaker, or HyperPod, and runs evaluation, optimization, and load tests.
Source-tracked catalog of abliterated, low-refusal, and community-reported open-weight and hosted language models
An F# tensor library for differentiable programming, machine learning, optimization, and probabilistic programming.
Index of source-tracked low-filter, abliterated, and community-reported language, image, and video model catalogs
On-premise risk engine for Keycloak Adaptive MFA: scores authentication attempts against 19 configurable signals with local ML inference and returns a step-up decision.
Decision-weighting AI for GameMaker. Utility scoring with response curves, per-target options, commitment, a frame-budget scheduler with priority tiers, and agents that learn from player choices: habit and preference models, re-ranking and prediction. Pure GML.
htop for Neural Networks: A terminal monitor for PyTorch layer activations and gradients
Reverse-mode automatic differentiation engine with DAG tape and chain rule backpropagation
Free multiple-choice quiz on AI and machine learning, from the basics to research topics. Every option explains why it's right or wrong. English and Spanish.
🐍 Learn every core Python concept for Machine Learning & Deep Learning in 2–3 hours. Hands-on Jupyter notebook with ML examples, practice tasks & solutions.
Bradley-Terry preference model computing choice probabilities, binary cross-entropy loss, and reward gradient updates
Reproducible text-classification pipeline - Hydra configs, DVC data, MLflow tracking and a scikit-learn grid search.
Multi-layer perceptron (MLP) feedforward inference with Xavier/Glorot initialization and activations
Reverse-mode automatic differentiation engine with DAG tape and chain rule backpropagation