Applied Data Science Program - Leveraging AI for Effective Decision Making by MIT Professional Education

This is a repository of my work during Advanced Data Science Program - Leveraging AI for Effective Decision-Making course by MIT-PE, as part of March 2024 cohort. It may include course material that was refered and any supplementary learning material.

The link to the course is https://professional-education-gl.mit.edu/mit-applied-data-science-course

Following were the main skills, to name few, acquired during the course:

• Python
• Machine Learning
• Deep Learning
• Neural Networks
• Artificial Intelligence
• Recommendation Systems

Following is the breakdown of the course modules where each module had a project (6 hands-on course projects, 1 Elective project, and 1 final Capstone project --> ~8 Projects in total):

Pre-work:

• Module: Introduction to Python (Python learning by mentors -- Python practical exercises and quizzes)
• Introduction to Data Science and AI (Video on-demand, chapter slides, and timed quizzes)

Online Classes by MIT Professors (Mentored Classes over the weekends by different mentors --> class revisions and project guidance etc. for each module):

Module 1: Foundations - Python and Statistics (1 hands-on Project)

• Python Foundations - Libraries: Pandas, NumPy, Arrays and Matrix handling, Visualization, Exploratory Data Analysis (EDA)
• Statistics Foundations: Basic/Descriptive Statistics, Distributions (Binomial, Poisson, etc.), Bayes, Inferential Statistics

Module 2: Data Analysis and Visualization (1 hands-on Project)

• Exploratory Data Analysis, Visualization (PCA and t-SNE) for visualization and batch correction
• Introduction to Unsupervised Learning: Clustering includes- Hierarchical, K-Means, DBSCAN, Gaussian Mixture
• Networks: Examples (data as network versus network to represent dependence among variables), determine important nodes and edges in a network, clustering in a network

Module 3: Machine Learning (1 hands-on Project)

• Introduction to Supervised Learning - Regression
• Introduction to Supervised Learning - Classification
• Model Evaluation - Cross Validation and Bootstrapping

Module 4: Practical Data Science (1 hands-on Project)

• Decision Trees
• Random Forest
• Time Series

Module 5: Deep Learning (1 hands-on Project)

• Intro to Neural Networks
• Convolutional Neural Networks
• Transformers

Module 6: Recommendations Systems (1 hands-on Project)

• Intro to Recommendation Systems
• Matrix
• Tensor, NN for Recommendation Systems

Module 7: Capstone Project (Final project to get certified)

• Milestone (The initial code - Jupyter Notebook format -- Google Colab)
• Final Submission (The final code - Jupyter Notebook format -- Google Colab and Final Report)
• Synthesis + Presentation

Self-paced Modules:

• Module 1: Generative AI (replaced by Demystifying ChatGPT and Applications)
• Module 2: ChatGPT and Generative AI: The Development Stack