2021 Master Class -【Computer Science】Python: Machine Learning & Computer Vision



Professor Introduction:


Mohammad Soltanieh-ha is a Clinical Assistant Professor at the Information Systems department at Boston University’s Questrom School of Business. Professor Soltanieh-ha obtained his Ph.D. in computational physics in 2015 from Northeastern University and his research interest revolves around computer vision applications of deep learning in automating histopathological diagnosis in cancer research as well as large scale computing and data science. His teaching experience involves data science programming, big data analytics, and applications of data science in business. 



Course Objectives:

  • Learn what algorithms, programming, artificial intelligence, machine learning, data science, and computer vision mean
  • Learn the impacts of machine learning and data science on society
  • Learn about the problems data science can solve and how the machine learning process, particularly computer vision works


Course Outcome:

This masterclass prepares the students to learn how to think programmatically in solving problems using data. Students will use their understanding of artificial intelligence, machine learning, and python to develop a unique project which utilizes these concepts. Previous examples of students who have completed this course have created a program which utilizes AI to identify traffic signs or to differentiate if a room is considered clean or messy. They will learn some of the modern applications of AI in computer vision and while working on that they will also enhance their programming skills in python which is the most widely used programming language in both academia and related industries.


Course Preparation: 

Students will need to complete the below pre-work before class begins. This work needs to be done prior to the start of the course. Pre-work covers the basics of programming in python. An overview of this material will be provided in the first class. 


Course Topics which will be covered:

  • Data science programming in Python
  • Machine learning and deep learning models
  • Computer vision – convolutional neural network (CNN)
  • Facial recognition system (or a similar problem): students will build a model that can classify images. The application area of such a model is limitless: people, medical images, food, animals, places, manufacturing, and many more


Course Outline:

Week 1

  • Introduction to machine learning and data science
  • Applications of machine learning and data science in industry and science
    • Assignment: pick a machine learning application and prepare a presentation
  • Basic mathematics for machine learning (regression)
  • Understand and develop the basic idea behind machine learning
    • Assignment: derive some of the mathematical foundations discussed in class
  • Regression & classification problems

Week 2

  • Examples and methods of machine learning classification problems
    • Assignment: implement a logistic regression method in Python
  • Neural networks and Deep learning
  • Examples and methods of neural networks model in Python
    • Assignment: implement a neural network model in Python
  • Convolutional Neural Networks (CNNs) and Deep Learning
  • Basics of CNNs and mathematics supporting it
    • Assignment: implement a CNN algorithm in Python using Keras framework

Week 3

  • Transfer learning – reusing pre-trained CNN models
  • Review session
  • Final presentation – Throughout the course, you will work on your project. Details will be given on day 4 of the class. During the last class, you will present your findings.


Teaching Materials:

An overview of basics programming in Python (Strongly recommended for students with no prior knowledge of programming in Python)

  • Deep Learning with Python by François Chollet
    • Chapter 1: What is Deep Learning?
    • Chapter 3: Getting Started with Neural Networks
    • Chapter 4: Fundamentals of Machine Learning 
    • Chapter 5: Deep Learning for Computer Vision
  • Slides
  • Code (GitHub repository) – notebooks 1-27 & 29


Post-Workshop Materials:

  1. Neural Networks and Deep Learning
  2. Improving Deep Neural Networks: Hyperparameter tuning, Regularization, and Optimization
  3. Structuring Machine Learning Projects
  4. Convolutional Neural Networks
  5. Sequence Models
  • Kaggle: continue with Kaggle competitions or other data science projects


🙋🏻‍♀️ Sign Up Here


For more information about Master Class, Click me 

Know More About Other Master Classes

2021 Master Class -【Technology & History】3D Modeling and VR

2021 Master Class -【Psychology】Introduction to Abnormal Psychology: Mental Illness

2021 Master Class -【Business】Tesla: International Business Management