Skip to content

KambhampatiAdvaith/FMML-Training

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

36 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Applied AI & ML Lab Exercises

IIIT Hyderabad – Certification Program | Hands-On Machine Learning & Deep Learning

Welcome to my repository of lab notebooks and projects completed as part of the Applied AI/ML Training Program by IIIT Hyderabad. This collection reflects my practical learning journey through core machine learning, neural networks, data processing, and algorithmic thinking — built from the ground up using Python and modern ML libraries.


Key Highlights

  • Core ML Algorithms implemented from scratch
  • Clean visualizations & intuitive explanations
  • Real-world data preprocessing and model tuning
  • Neural Network implementation using TensorFlow/Keras
  • Modular, reproducible, and Colab-compatible notebooks

Modules & Topics

Module Focus Areas
Module 1 Data Transformation, Encoding, Feature Scaling
Module 2 PCA, Manifold Learning, t-SNE
Module 3 Distance Metrics, KNN from scratch, Text Classification
Module 4 Gradient Descent, Perceptron, Linear Regression
Module 5 Clustering, Probability Theory
Module 6 Neural Networks, Activation Functions, Feedforward Design
Add-ons Speech Processing, Linear Algebra Review, NN Tutorials

Tech Stack

  • Language: Python

  • Environment: Google Colab / Jupyter Notebook

  • Libraries:

    • Data: NumPy, Pandas, Matplotlib, Seaborn
    • ML: scikit-learn, TensorFlow, Keras

Objectives

  • Build strong foundations in machine learning and AI
  • Apply concepts through code, rather than just theory
  • Develop confidence in creating models from scratch
  • Tackle real datasets and uncover insights through exploration

About the Program

This repository is part of the 6-month Applied AI & Machine Learning Certification Program by IIIT-Hyderabad, focused on hands-on implementation, algorithmic thinking, and problem-solving with code.


Feel free to explore, run the notebooks, and build upon them!

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published