Courses completed between September 2018 and November 2019.
Introduction to Artificial Intelligence(AI): This course covered the fundamentals of Machine Learning, Azure Machine Learning Studio, Text processing, Introduction of Natural Language Processing, Working with Images and Videos, Introduction to Bots, Building Intelligent Bots, and Beyond the Basics.
Introduction to Python for Data Science: This course started with writing “Hello Python!” and covered the topics of Variables and Types, Python Lists, Functions, Methods, Packages, Numpy, 2D Numpy Arrays, Basic Statistics with Numpy, Basic Plot with Matplotlib, and Histogram. The course was taught by DataCamp instructors. Teaching materials were stored in the DataCamp site.
Essential Mathematics for Artificial Intelligence – Python Edition: The course covered Algebra Fundamentals, Quadratic Equations and Functions, Differential Calculus Foundations, Differentiation and Derivatives, Vectors, Matrices, Statistics Fundamentals, and Probability.
Ethics and Law in Data and Analytics: This course taught Data’s Ethical Foundations, Data’s Legal Foundations, Ethical Data Practice, Data Bias and Identity, Data Privacy and Power, Business and Ethical Data Use, Business and Data Privacy, and AI and Design.
Data Science Research Methods – Python Edition: The course covered the Research Process, the Psychology of Providing Data, Planning for Analysis, Power and Sample Size Planning, Research Practices, Frequency Claims, Association Claims, Causal Claims, Survey Design and Measurement, Reliability and Validity, Bivariate and Multivariate Designs, Between and Within Groups Experimental Designs, and Factorial Designs.
Principles of Machine Learning – Python Edition: This introduced to Machine Learning. The topics were High-Level Data Science Process, Overview of Machine Learning, Exploratory Data Analysis for Regression and for Classification, Data Preparation, and Cleaning, Feature Engineering, Regression, Classification, Principle of Model Improvement, Techniques for Improving Models, Dimensionality Reduction, Introduction to Decision Trees, Ensemble Methods, Neural Networks, Support Vector Machines(SVMs), Bayes Theorem, and Clustering.
Deep Learning Explained: The course covered Multi-class Classification using Logistic Regression, Multi-Layer Perception, Convolution Neural Network, Recurrent Neural Network, and Text Classification with RNN and LSTM.
Reinforcement Learning Explained: The course covered Application of Reinforcement Learning, introduction to Reinforcement Learning, Comparisons, Elements of RL, Bandits Framework, Regret Minimization, Bridge to Reinforcement Learning, Agent and Environment Interface, Markov Decision Process, Basics of Dynamic Programming, DP Observations, Policy Evaluation, Policy Optimization, Why Use Function Approximation, Linear Function Approximation, RL with Deep Neural Networks, Extensions to Deep Q-Learning, Introduction n to Policy Optimization, Likelihood Ration Methods, Variance Reduction, and Actor-Critic.
We found that this course and materials were confusing and do not have sufficient information for learners. Before completed the course, we decided to take additional Reinforcement Learning courses by David Silver
Computer Vision and Image Analysis: The topics were Image Processing Fundamentals, Working with Images, Introduction to Image Classification, Deep Learning for Image Classification, Dealing with Overfitting, Transfer Learning,. Object Detection, and Semantic Segmentation.
Natural Language Processing: The topics were Introduction to Classical Natural Language Processing, Language Understanding with Recurrent Networks, Sequence to Sequence Networks with Text Data, and Deep Structured Semantic Modelling with LSTM Networks.
Microsoft Professional Capstone – Artificial Intelligence: The final capstone project was designed to demonstrate the learnings and knowledge from the previous courses. The goal of the project was to design a model that could classify documents into multiple relevant categories over 18,000 documents from the World Bank along with categories for each document. For the details of the project, please see the link provided in the title.