Machine Learning & Deep Learning

A collection of Jupyter notebooks covering core machine learning and deep learning concepts, from classical algorithms to modern architectures.

📁 Repository Structure

Classical Machine Learning

Folder	Description
Regression/	Linear regression (manual, scikit-learn, TF/Keras)
Classification/	Classification with scikit-learn and Keras
Clustering/	Unsupervised clustering algorithms
DimensionalityReduction/	PCA and dimensionality reduction techniques

Deep Learning

Folder	Description
NeuralNetworks/	Fundamentals — Sequential, Functional API, Model Subclassing, overfitting
CNN/	Convolutional Neural Networks — VGG16, image classification, handwritten digits
RNN/	Recurrent Neural Networks — LSTM, email classification

Natural Language Processing

Folder	Description
NLP/	Sentiment analysis, text classification, Word2Vec, LDA, NLP basics
Transformers/	Transformer architectures — encoder, decoder-only, Vision Transformer
Finetuning/	Model finetuning techniques
LangChain/	LangChain framework practice

Foundations

Folder	Description
DataFundamentals/	DataFrames, plotting, statistics
DataSets/	Datasets used across notebooks (CSV, image data)

🛠️ Setup

pip install numpy pandas matplotlib scikit-learn tensorflow keras torch transformers langchain

📝 Usage

Open any notebook with Jupyter:

jupyter notebook