ML & DL Daily Practice 🚀

This repository contains my daily practice and learning of
Machine Learning (ML) and Deep Learning (DL) concepts using Python.

The focus of this repository is to understand concepts clearly, implement algorithms step by step, and build a consistent learning habit while creating a useful public resource for beginners.

---

🎯 Goals

• Build strong fundamentals in Machine Learning & Deep Learning
• Practice daily using small, focused problems
• Learn algorithms conceptually (not just library usage)
• Maintain consistency in learning and GitHub contributions
• Create a beginner-friendly reference for ML/DL concepts

---

🧠 What This Repository Contains

• Simple and well-commented Python implementations
• “From scratch” implementations to understand core logic
• Library-based implementations for comparison
• Clear explanations written in easy-to-understand language
• Experiments and observations from daily practice

---

🛠️ Tech Stack

• Python
• NumPy
• Pandas
• Scikit-learn
• PyTorch
• Matplotlib / Seaborn

---

Each topic folder includes:

• Python implementation files
• A README explaining the concept in simple terms

---

📘 How to Use This Repository

• Start with ML → Regression → Linear Regression if you are a beginner
• Read the README inside each folder before going through the code
• Run the code, experiment with parameters, and observe results
• Use this repository as a learning guide or reference

---

🌱 Who This Repository Is For

• Beginners learning Machine Learning or Deep Learning
• Students pursuing AI / Data Science related fields
• Anyone who wants to understand how ML/DL works internally
• Learners who prefer understanding over memorization

---

⭐ Note

This repository is maintained as a daily learning log and will grow gradually with consistent practice.

Learning, clarity, and consistency are the priorities.

---

🧪 Experiments & Progress

This section lists the experiments and concepts covered so far. It is updated daily as part of the learning process.

🟦 Machine Learning – Fundamentals

• [1] Mean, Median, Variance
• [2] Standard Deviation & Normal Distribution
• [3] Covariance vs Correlation
• [4] Vector & Matrix Operations
• [5] Dot Product
• [6] Cost/ Loss Function Intuition
• [7] Gradient Descent

🟩 Machine Learning – Regression

• [8] Simple Linear Regression (From Scratch)