Welcome to my Machine Learning & Deep Learning learning journey.
This repository documents my step-by-step progress as I learn, experiment, and build projects using Machine Learning (ML) and Deep Learning (DL) concepts.
The goal is not just to finish tutorials, but to understand the fundamentals, write clean code, and build real intuition.
This repo will grow over time as I move from basics → intermediate → advanced topics.
- Build a strong foundation in ML & DL
- Learn concepts by implementing them from scratch
- Practice using popular libraries (NumPy, Pandas, PyTorch / TensorFlow)
- Track progress in a transparent and structured way
- Create a solid base for future projects and research
- Linear Regression
- Logistic Regression
- Gradient Descent
- KNN
- Decision Trees
- Naive Bayes
- Support Vector Machines (SVM)
- Model evaluation & metrics
- Neural Networks fundamentals
- Backpropagation
- Activation functions
- CNN basics
- RNN basics (later)
- Training & optimization techniques
- Linear Algebra (vectors, matrices)
- Probability & Statistics
- Calculus (intuition-based)
- Language: Python
- Libraries: NumPy, Pandas, Matplotlib, Scikit-learn
- Deep Learning: PyTorch / TensorFlow (later)
- Environment: Jupyter Notebook & Python scripts
Each folder represents a clear learning stage or concept.
Notes, code, and experiments are kept together for clarity.