Skip to content

AyushDineshRathi/Project

Repository files navigation

Machine Learning Journey 🚀

This repository is a living collection of my work in Machine Learning, Deep Learning, NLP, and Generative AI. Instead of being a fixed project archive, this repo grows continuously as I learn new concepts, build experiments, and implement ideas from scratch.

It represents a hands‑on learning journey — from core algorithms to advanced deep learning and real‑world applications.


What this repository is about

  • Practical implementations of ML, DL, and NLP concepts
  • Small experiments, mini-projects, and full applications
  • Implementations from scratch to understand core logic
  • End-to-end projects with training, evaluation, and deployment
  • Continuous additions as new topics are explored

This is not a static portfolio — it is an evolving technical notebook of progress.


Key areas covered

Machine Learning

  • Regression and classification problems
  • Real-world prediction systems
  • Data preprocessing and feature engineering

Deep Learning

  • Artificial Neural Networks (ANNs)
  • Convolutional Neural Networks (CNNs)
  • Computer vision tasks (e.g., handwritten digit recognition)

Natural Language Processing (NLP)

  • Sentiment analysis
  • Recommendation systems
  • Duplicate question detection
  • Transformer-based models

Generative AI

  • LLM-based applications
  • Retrieval-augmented systems and chatbots
  • Vector search using FAISS

Implementation from Scratch

  • Gradient descent
  • Neural networks
  • Core ML algorithms and mathematical intuition

Purpose & Goals

  • Strengthen fundamentals through hands-on coding
  • Build an applied ML/AI portfolio with practical examples
  • Experiment with new architectures and ideas
  • Track personal learning progress over time

How to use this repository

  1. Explore any project folder or notebook.
  2. Open notebooks to see experiments and explanations.
  3. Run applications using the provided scripts where available.
  4. Use projects as reference implementations.

Typical Python project setup:

python -m venv .venv
# On macOS / Linux
source .venv/bin/activate
# On Windows (PowerShell)
.\.venv\Scripts\Activate.ps1
# On Windows (cmd)
.\.venv\Scripts\activate

pip install -r requirements.txt
python app.py

Tip: Check each project folder for a requirements.txt and a small README with project-specific instructions.


Philosophy

Learn → Implement → Experiment → Improve → Repeat

Each project is an opportunity to deepen understanding and iterate on ideas. Some experiments are intentionally rough — learning is the focus.


Future additions

  • Transformer-based applications
  • Multimodal AI systems
  • Real-time ML deployments
  • Research-inspired implementations and end-to-end AI products

About me

I’m a student and AI enthusiast building projects across Machine Learning, Deep Learning, NLP, Generative AI, and full-stack AI applications.


License

This repository is offered for learning and reference purposes. You may use the code for educational or non-commercial projects.


About

This repository is offered for learning and reference purposes.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors