shsarv/Machine-Learning-Projects

This repository showcases a selection of machine learning projects undertaken to understand and master various ML concepts. Each project reflects commitment to applying theoretical knowledge to practical scenarios, demonstrating proficiency in machine learning techniques and tools.

What it solves

This repository provides a structured, hands-on learning resource for developers and students to explore machine learning through practical application. It solves the problem of finding cohesive, end-to-end examples that demonstrate how to move from raw data to a functional, deployed model.

How it works

The repository contains 26 distinct projects organized by domain, such as healthcare, computer vision, and natural language processing. Each project follows a standardized structure, including raw data, Jupyter notebooks for exploration, scripts for training and prediction, and configuration files for deployment. Users can clone the repository, set up a virtual environment, and run the provided code locally or deploy web-based apps using Flask.

Who it’s for

This collection is designed for data science students, machine learning enthusiasts, and developers looking to build a portfolio. It caters to various skill levels, ranging from beginner-friendly classical prediction tasks to advanced deep learning and computer vision implementations.

Highlights

  • 26 end-to-end projects covering 6 major AI domains.
  • Consistent project structure including data, notebooks, and deployment-ready code.
  • Includes both web-based applications and Jupyter notebook tutorials.
  • Covers a wide tech stack including Scikit-learn, TensorFlow, PyTorch, OpenCV, and Flask.
  • Clearly labeled projects by difficulty level (Beginner, Intermediate, Advanced).

Related

  • Project
    meta-recsys/generative-recommenders

    Generative Recommenders is a research‑grade code base that reframes recommendation as a generative modeling task. It introduces the HSTU/HSTU‑Ultra attention layers and the M‑FALCON training algorithm, enabling trillion‑parameter sequential models that run 2‑3× faster (and up to 10×‑1000× overall) on modern GPUs. The repo provides scripts to reproduce state‑of‑the‑art results on MovieLens and Amazon datasets, tools for synthetic 3‑billion‑rating data, and FP8‑quantized kernels for production‑level inference. Apache 2.0 licensed and tested on Ubuntu 22.04, CUDA 12.4, Python 3.10.

  • Project
    philipperemy/keras-tcn

    A Keras implementation of Temporal Convolutional Networks (TCN) that provides a more stable and parallelizable alternative to LSTMs and GRUs for long sequence modeling.

  • Project
    youngfish42/Awesome-FL

    A curated, community-maintained index of federated learning resources — papers by venue and topic, frameworks, datasets, surveys, tutorials, and events — now updated less frequently since the main author completed his PhD, with contributions welcome.

  • Project
    harry7557558/spirula-studio

    Spirula Studio is an all-in-one, cross-platform application for training 3D Gaussian Splatting models from photos and videos without requiring complex Python or PyTorch setups.