Course Logistics and Introduction: CSN-526 Machine Learning
Course Logistics and Introduction: CSN-526 Machine Learning
CSN-526
Machine Learning
2
Course Logistics
▪ Course Name: Machine Learning (CSN-526)
▪ An introductory course – supposed to be your first intro to the subject
▪ Course-related announcements will be sent on the class mailing list (and also on
Microsoft Teams)
▪ Timings:
Lectures: Monday (02:00 - 02:55), Tuesday (02:00 - 02:55), Thursday (02:00 - 02:55)
Tutorials: Wednesday (04:05-05:00), Wednesday (05:05 - 06:00)
3
Grading
▪ https://www.cse.iitk.ac.in/users/piyush/courses/ml_autumn18/index.html
▪ https://github.com/purushottamkar/ml19-20w
P(“cat”|image) P(“dog”|image)
14
Overfitting = Bad ML
▪ Doing perfectly on training data is not good enough
Example from “Compilation error repair: for the student programs, from the student programs”, Ahmed et al (2018)
21
Good ML Systems Should be Fair and Unbiased
▪ Good ML should not just be about getting high accuracies
▪ Should also ensure that the ML models are fair and unbiased
Criminals?
Not Criminals?
An image captioning Don’t want a self-driving car Don’t want a predictive policing
system should not always that is more likely to hit black system that predicts criminality
assume a specific gender in people than white people using facial features
examples like the above