This repository documents my journey of learning machine learning step by step, starting from the fundamentals and gradually moving toward more advanced topics and real-world systems.

The focus of this repo is understanding how things work internally, not just using libraries as black boxes.

Foundational algorithms and concepts such as:

• Linear & Logistic Regression
• Decision Trees
• Bagging, Random Forest
• Boosting (AdaBoost, Gradient Boosting)
• K-Means and other clustering methods
• Bias–Variance tradeoff
• Model evaluation and metrics

📁 Folder: ClassicalML/

Core deep learning concepts built on top of classical ML:

• Neural Networks (ANN)
• Backpropagation & optimization
• Regularization techniques
• Practical implementation using modern frameworks

Domain-specific learning:

• Computer Vision (CNNs, feature extraction, vision models)
• Natural Language Processing (text processing, embeddings, sequence models)
• Attention mechanisms and Transformers

Exploring generative models and modern AI systems:

• Language models
• Diffusion-based approaches
• Practical GenAI workflows

Bridging models with real-world systems:

• APIs and model serving
• Experiment tracking
• Containerization and deployment
• Monitoring and scalability

• Build a strong conceptual foundation
• Understand why algorithms work, not just how to call them
• Practice structured thinking around data, models, and systems
• Progress from algorithms → applications → production-ready pipelines

This repo will evolve as my learning progresses.

• Python
• NumPy, Pandas, Matplotlib
• Scikit-learn
• Deep learning frameworks
• Backend APIs
• Deployment & infrastructure tools

This repository reflects learning-in-progress. Concepts are added gradually, refined over time, and revisited as understanding deepens.

If you're also learning or exploring similar topics, feel free to explore the repo or reach out.