M

machine-learning

API4AI is cloud-native computer vision & AI platform for startups, enterprises and individual developers. This repository contains sample mini apps that utilizes People Photo Background Removal API provided by API4AI.

This is an extension integrated machine learning to provide security from scam and other phishing links and domains.

Academic NLP project focused on multilingual text summarization using Transformer-based deep learning models and natural language processing techniques.

A production-grade machine learning system for classifying celestial objects — stars, galaxies, and quasars — from 500,000 photometric observations sourced from the Sloan Digital Sky Survey (SDSS DR18). The pipeline covers LOF-based outlier detection, SMOTEENN class balancing, and SelectKBest feature selection, with six classifier configurations benchmarked against each other. Random Forest achieved the highest accuracy at ~99.51%, while LightGBM was selected for deployment due to its faster inference, smaller footprint, and clean ONNX export path. The system is fully containerized with Docker, backed by a CI/CD pipeline, and served live via a Gradio interface on Hugging Face Spaces.

Multi-source RAG pipeline with hybrid vector + keyword retrieval, LLM-powered concept knowledge graph, adaptive search weighting, and evaluation framework.

Hệ thống phát hiện bất thường trên log HDFS bằng machine learning truyền thống, hỗ trợ tiền xử lý, benchmark, huấn luyện, đánh giá và dự đoán trên nhiều mô hình

A full-stack web application designed to bridge the gap between complex mathematical expressions and clean, compilable LaTeX code. This project leverages Machine Learning (Hugging Face models) to take raw text or messy equations and transform them into optimized, industry-standard LaTeX.

The system features a ReactJS frontend for real-time editing and a Python/Flask backend. To keep the deployment lightweight and free-tier friendly (Render/Railway), the project utilizes an External API Proxy Pattern for PDF generation, eliminating the need for a 2GB+ local TeX distribution.

AI-Powered Anti-Cheat Research Tool - Train your own AI to detect suspicious gameplay patterns using Vision Transformers and audio analysis. Fully local processing, no cloud uploads. Perfect for competitive gaming research and anti-cheat development.

The efficient alternative to Neural Networks. Implements SLRM (Segmented Linear Regression Model) for neural compression and non-linear data modeling, achieving high precision with a fraction of the parameters of a traditional ANN.

BrotServer é um projeto de Modern Data Stack on‑premise que integra hardware de nível empresarial (Dell PowerEdge T440) e a plataforma open source Cloud Brots para desenvolvimento, ciência de dados, BI, IA e ensino. O repositório versiona o livro técnico oficial, que documenta a arquitetura, os padrões de Ops (GitOps, DataOps, ModelOps, ResearchOps, AIOps), os componentes principais (Kubernetes/RKE2, Longhorn, Traefik, MinIO, PostgreSQL, Superset, Moodle, Ollama, etc.) e as boas práticas de operação, com foco em soberania de dados, reprodutibilidade científica e uso de uma única porta de acesso.

[2025] Autonomous Claude Code plugin with pattern learning and skill auto-selection. Features 27 specialized agents across 4 collaborative groups, quality control automation, and intelligent task execution without human approval at each step.

Training the system with binary classification to classify cookies as correctly oriented or flipped Topics: #algorithm #image-2d #machine-learning #sample #sick-appspace

Training a set of cereal types and classifying a test set. Topics: #algorithm #image-2d #machine-learning #sample #sick-appspace

Loading a trained neural network and running predictions on locally saved images. Topics: #algorithm #image-2d #machine-learning #sample #sick-appspace

Example showing the use of a pretrained classification network together with an EdgeMatcher to inspect multiple image regions. See also the available tutorials on the SICK support portal. Topics: #algorithm #image-2d #machine-learning #deep-learning #neural-network #sample #sick-appspace #edgematcher #locator #matching

Example showing the use of a pretrained classification network. See also the available tutorials on the SICK support portal. Topics: #algorithm #image-2d #machine-learning #deep-learning #neural-network #sample #sick-appspace

Auctions & bids online live system

Syetem to predict taxi fare in bhutan

It contains all my projects I made in the past 2 years, including smaller programs and bigger applications, from backend to frontend, mainly coded in Java and Python.

An Active Learning framework for Drug Discovery with the ability to create targeted models for particular experiments