Course Syllabus

Overview

Students should watch Udacity course videos according to the following schedule. It is recommended for students to do lab sessions on the schedule by yourself as early as possible since some of homework may cover the lab materials scheduled later than the homework. For the online video lectures, CS/CSE students should go to Udacity while Analytics students should navigate to Edx instead, please check details on Canvas.

Schedule

Week #DatesVideo lessonsLabDeliverable Due
1Aug 19-23[1. Intro to Big Data Analytics], [2. Course Overview][Scala Basic]
2Aug 26-30[3. Predictive Modeling][Hadoop & HDFS Basics]HW1 Due (Sep 1)
3Sep 2-6[4.MapReduce]& [HBase][Hadoop Pig & Hive]
4Sep 9-13[5.Classification evaluation metrics], [6.Classification ensemble methods]HW2 Due (Sep 15)
5Sep 16-20[7. Phenotyping], [8. Clustering][Spark Basic], [Spark SQL]
6Sep 23-27[9. Spark][Spark Application] & [Spark MLlib]HW3 Due & Project Group Formation & Project Requirements Release (proposal/draft/final) (Sep 29)
7Sep 30-4[10. Medical ontology][NLP Lab]
8Oct 7-11[11. Graph analysis][Spark GraphX]Project Proposal Due (Oct 13)
9Oct 14-18[12. Dimensionality Reduction], [13. Patient similairty], [14. DNN][Deep Learning Lab]HW4 Due (Oct 20)
10Oct 21-25[15. CNN], [16. RNN]
11Oct 28- Nov 1Potential Guest LectureHW5 Due (Nov 3)
12Nov 4-8Potential Guest Lecture
13Nov 11-15Potential Guest LectureProject Draft Due (Nov 10)
14Nov 18-22Project Discussion
15Nov 25-29Project DiscussionFinal Exam (Dec 3)
16Dec 2-6Project SubmissionFinal Project Due (code + presentation + final paper) (Dec 8)

Previous Guest Lectures

See RESOURCE section.