This repository contains tutorial notes, lab and assignment code implementations completed as part of Andrew Ng's renowned Machine Learning Specialization, Deep Learning Specialisation And MLOps Specialisation on Coursera. This specialization provides an excellent foundation in machine learning theory and practice.
The Machine Learning Specialization covers the following core topics:
-
Supervised Learning:
- Linear Regression
- Logistic Regression
- Regularization
- Neural Networks
-
Unsupervised Learning:
- Clustering
- Dimensionality Reduction
-
Special Applications:
- Recommender Systems
- Large-Scale Machine Learning
-
Advice and Best Practices:
- How to diagnose errors in an ML system
- Building effective machine learning projects.
-
Deep Learning Specialisation And Concepts
- Tensorflow
- Natural Language Processing
- Convolutional Neural Networks
- Sequence Models
-
MLOps Specialisation And Concepts
- ML In Production
- Modelling Pipelines
- Deploying ML Models
The repository is organized as follows:
-
Specialisation One: Machine Learning Specialization
-
Specialisation Two: Deep Learning Specialization By DeepLearning.AI
-
Specialisation Three: Machine Learning Engineering for Production (MLOps) Specialization
The notes.md files in each week summarize key concepts, formulas, and may include code snippets or examples.
Lab assignments are provided either in Python scripts (.py) or Jupyter Notebooks (.ipynb). These files include comments and explanations to guide you through the implementations.
- Basic Python programming
- Foundational knowledge of math (linear algebra, calculus)
- Clone the repository.
- Use the notes for review and theoretical understanding.
- Complete the lab assignments to solidify practical implementation skills.
- Consider contributing your own solutions or improvements!
Please respect the course's honor code and policies regarding distribution of course materials. This repository is intended for personal study and reference.