Welcome to my comprehensive repository for the prestigious Machine Learning Specialization offered by DeepLearning.AI and Stanford University on Coursera. This repository is a curated compilation of all my course projects, detailed assignments, and insightful notes. Each component is meticulously documented as I advance through this rigorous program, designed to sculpt novice learners into experts in the field of Machine Learning.
The contents of this repository represent my personal journey and original work throughout the Machine Learning Specialization. They are provided for educational purposes and to showcase my learning progression. While this material can be used for inspiration and learning, I strongly discourage and denounce any acts of plagiarism. Please respect the effort and creativity put into this work by not copying any part of it for your own submissions in similar or any educational courses. Let's maintain integrity and foster an environment where learners can thrive through genuine effort and originality.
This repository is not just a collection of solutions but a gateway to understanding the intricacies of machine learning. It serves as a dynamic resource for anyone interested in the deep and transformative power of machine learning technologies. Here, you will find detailed explanations and implementations that elucidate complex concepts and demonstrate their application in real-world scenarios.
Feel free to explore the repository, learn from it, and contribute to the ongoing discussion of machine learning innovation. If you have any questions or would like to discuss the projects further, please reach out through my GitHub contacts.
- Week 1: Introduction to machine learning, linear regression, cost functions, and gradient descent.
- Week 2: Multiple linear regression, cost functions for multiple features, feature engineering, and polynomial regression.
- Week 3: Logistic regression, understanding classification vs. regression, regularization techniques to combat overfitting.
- Week 1: Building neural networks for binary classification, neural network architectures, and vectorization.
- Week 2: Multi-class classification with neural networks, activation functions, and optimizations.
- Week 3: Data partitioning strategies, bias-variance trade-off, regularization, and data-centric AI approaches.
- Week 4: Decision trees, random forests, XGBoost, choosing between model types.
- Week 1: K-means clustering, anomaly detection, supervised vs unsupervised decision-making.
- Week 2: Building recommender systems using collaborative and content-based methods.
- Week 3: Constructing a deep reinforcement learning model (Deep Q Network).
Each folder in this repository corresponds to a course and week in the specialization. To run the programs, navigate to the appropriate directory and execute the Jupyter Notebook scripts.
Feel free to fork this repository if you have suggestions or improvements. Contributions to the project are always welcome!
Thanks to DeepLearning.AI and Stanford University for creating this excellent specialization. Hats off to the course instructors including Andrew Ng and everyone involved in the course design and implementation.