model-training

Resource scheduling and cluster management for AI

[NVIDIA ONLY] Optimized Training script for Ace-Step with low VRAM support for local GPUs. (Requirements 8GB VRAM)

NeuralNet is a full-stack visual deep learning studio where you design neural networks with drag-and-drop nodes, compile to Keras, train with real TensorFlow metrics, and deploy secure prediction APIs.

🧠 Dedicated deep learning framework in NodeJS

BrainVision AI is a fully client-side brain tumor classifier that runs entirely in the browser using ONNX Runtime Web. It processes MRI images locally, preserving privacy while delivering fast and reliable predictions. The project includes a responsive UI, multi-language support, theme switching, and a complete training pipeline with Keras and ONNX

This project monitors robotic welding quality by analyzing arc sound in real time. An unsupervised Isolation Forest, trained only on normal audio, flags acoustic anomalies using RMS/MFCC features, streaming live PASS/FAIL results to a web dashboard via Flask and Socket.IO.

A full-stack Machine Learning web application for generating synthetic epidemiological data, training multiple ML models, and predicting disease outbreak risk through an interactive dashboard.

Auto driving car simulation using neural networks and model training. Used html canvas for draw elements and javascript for train the model. not any third party libraries used.

Thumbnail design platform that finds top-performing thumbnails across the web. Upload your image, enter a title — get the top 5 highest-performing thumbnails with matching keywords. Design thumbnails that actually get clicks! Built with MERN stack (MongoDB, Express, React, Node.js).

Open-source AI Model Builder launcher, documentation, extensions, and secure private-core distribution by Reallexi LLC.

Fast & Lightweight Model Training Platform

Learn the basics of neural networks by training a model on XOR and AND operations

Vanilla JavaScript library for math utilities, array/matrix manipulation, and neural network modeling. Created to develop a fundamental understanding of neural network architecture, training, activations, and optimization while developing my ability to utilize linear algebra and JavaScript in future projects.

IoT smart parking platform with ML-powered occupancy forecasting. React + Django REST API, scikit-learn Random Forest, dynamic pricing, and ESP32-ready sensor integration. Built for airport-style multi-zone parking (NMIA).

A reproducible ComfyUI toolkit for FLUX and SD1.5 LoRA—from captioning to training and validation. | 可复现的 ComfyUI LoRA 工具包：覆盖 FLUX/SD1.5 打标、训练与效果验证。

An AI model trained to recognize Tic-Tac-Toe board and also handles game logic

This group project aims to predict the fatality of an accident given a certain input (time/weather condition/etc.) using machine learning models and Flask.

🧠 Classify brain tumors in your browser with BrainVision AI — a fast, privacy-focused tool using client-side machine learning for accurate diagnostics.

This repository is created for learning purposes and contains code adapted from a course. It serves as a reference for my personal learning journey. For the original repository and resources, please check out .https://github.com/charliegerard/fem-ml-workshop

A curated collection of machine learning projects covering data preprocessing, model training, evaluation, and experimentation workflows.