Welcome to my personal learning journey through Machine Learning (ML), Deep Learning (DL), and Computer Vision (CV), primarily based on Kaggle Learn and practical hands-on coding. This repository includes well-structured notebooks and code along with explanations and references.
Status: Completed ✅
This course covers the fundamentals of machine learning and introduces concepts using decision trees and random forests.
Topics:
- Introduction to Machine Learning
- How Models Work (Decision Trees)
- Model Validation
- Underfitting & Overfitting
- Random Forests
- Feature Engineering Basics
- Data Leakage
- Final Project
Status: Completed ✅
This course builds on the basics with a focus on handling missing data, categorical variables, and using XGBoost.
Topics:
- Missing Values: Drop & Impute
- Handling Categorical Variables: Drop, Ordinal Encoding, One-Hot Encoding
- Pipelines in Scikit-Learn
- Cross-Validation
- XGBoost
- Feature Importance
- Advanced Data Leakage (Target leakage, Train-test contamination)
- Final Project
Status: Completed ✅
This course introduces neural networks using PyTorch and focuses on core concepts like activation, optimization, and regularization.
Topics:
- A Single Neuron & Linear Units
- Fully Connected Networks
- Activation Functions
- Sequential Models
- Loss Functions
- Optimizers (SGD)
- Learning Rate & Batch Size
- Overfitting & Underfitting
- Learning Curves
- Early Stopping
- Dropout & Batch Normalization
- Classification Task (Final Project)
Status: Coming Soon 🔜
I will begin this course after completing documentation and final touches for the above modules.
ml-dl-computer-vision-journey/
│
├── README.md
├── machine-learning/
│ ├── 01_intro-to-ml/
│ └── 02_intermediate-ml/
│
├── deep-learning/
│ └── 03_intro-to-dl/
│
├── computer-vision/ # Coming Soon
│
└── datasets/ # Custom or Kaggle datasets (if any)