Introduction to Machine Learning

Title Introduction to Machine Learning
Quarter Summer 2017 (July 2017)
Instructor Dr Adam Ginensky (adam.ginensky@acads.org)
Syllabus Course Description
This is a fast paced 12 week course in Machine Learning for individuals with background in Statistics and Probability. The course is an introductory course in supervised learning and will focus on Regression and Classification techniques. The concepts taught during lectures will be implemented during TA sessions. This course will use R for all programming assignments.

Course Contents
  • Overview of statistics- prediction versus description
  • Linear Regression and Regularized Regression techniques
  • Bias-Variance TradeOff & Sampling methods
  • Model Paramater techniques (bootstrapping & cross validation)
  • Trees, Random Forests and Gradient Boosting
  • Support Vector Machine
  • Neural Nets including an introduction to Deep Learning
  • Using the caret package and similar tools for Model Selection
Course Objectives:
At the completion of the course, students will be able to do the following:
  • Select most appropriate predictive model without overfitting
  • Understand Bias Variance Trade off
  • Correctly estimate model parameters
Instruction Format Coursework will have following four important components:
  • Weekly tasks
    • The course instructor will provide reading material, short videos explaining key concepts and lecture notes to be completed at home
    • Instructor will hold regular video conferences to go over concepts where the students need help
  • Weekly Sessions with Teaching Assistants. The purpose of these sessions will be:
    • Discussion on topics from the week
    • Working in small groups on a problem and presenting solution to the class. Other groups will be required to challenge the concepts and methodology used for problem solving
    • Working on group and individual projects
    • Assignment discussions
    • Quizzes and Exams
  • Reading Assignment and homework for the week
  • Virtual office hour with TA/Instructor via video conferencing
Assessment A letter grade A,B,C,D or F for the course will be decided based on

Projects: 40% of the final grade

  • 2 group projects and 2 individual projects
Mid Term Exam: 10% of the final grade
  • 30 minutes duration which will include both multiple choice and subjective problems
Final Exam: 15% of the final grade
  • 30 minutes duration which will include both multiple choice and subjective problems
Homework: 20% of the final grade
  • There will be 6-8 homework which will be manually graded and feedback will be provided
Quizzes: 10% of the final grade
  • There will be 4 quizzes which will have multiple choice format
Class Participation:10% of the final grade
  • Your participation will be evaluated based on lab discussion, questions/comments, replies on the discussion forum and teamwork on the group projects
TextBook Introduction to Statistical Learning, James Witten, Hastie and Tibshirani
Pre-Requisite Prior experience with R, strong background in Statistics and Probability
Time Lecture Time:8:00 pm – 9:30 pm EST, Wednesday evenings
Lab Time:8:00 pm – 9:30 pm EST, Monday evenings
Virtual Office Hour time:TBA
Location   Online
TA Information TBA
Effort Required 8-10 hours per week
Certification Participants will receive an instructor-signed certificate with a Pass grade if they score 50% and will receive Pass with distinction above 80%