CMSC  422  Introduction to Machine Learning


Class:  T, Th......11:00am-12:15 pm (CSI 2120)


Instructor: Ramani Duraiswami E-mail: ramani AT;

Office Hours:  Wednesdays 12:00 noon - 1:15, in AVW 3361. (you must confirm I am there before coming via a private message on Piazza)


TA: Yang Jiao; E-mail: jiaoyang.tju AT

Office Hours: 1:00 PM to 3:00 PM on Fridays, in AVW 3368


Textbook:  A Course in Machine Learning (Required):

PIAZZA for peer-to-peer discussions/assistance.




Prerequisites: Programming, algorithms, advanced calculus. 


Description in the catalog: Machine Learning studies representations and algorithms that allow machines to improve their performance on a task from experience. This is a broad overview of existing methods for machine learning and an introduction to adaptive systems in general.

Collaboration Policy:  You may study together and discuss problems and methods of solution with each other to improve your understanding. You are welcome to discuss assignments in a general way among yourselves, but you may not use other students' written work or programs. Use of external references for your work should be cited. Clear similarities between your work and others will result in a grade reduction for all parties. Flagrant violations will be referred to appropriate university authorities.


You are responsible for checking this page, Piazza and Canvas.

Policy: Honor code

Previous versions of this course: (for reference)  2016 (Prof. Carpuat); 2013 (Prof. Daume' III)

All assignments will be posted on Canvas
All readings will be based on version 0.99 of the CIML book
All discussions will be on Piazza

1 26 Jan Introduction
2 31 Jan Supervised Learning Concepts
2 Feb
Decision Trees

7 Feb Limits of learning; Underfitting/Overfitting CIML 1, CIML 2
3 9 Feb Geometry and nearest neighbors CIML 3-3.3

14 Feb K-means clustering CIML 3.4-3.5
4 16 Feb Perceptron 1 CIML 4-4.5

21 Feb Perceptron 2 (proof of convergence) CIML 4.5-4.7
5 23 Feb Practical issues : debugging and evaluation
CIML 5-5.5
28 Feb Practical issues: evaluation and imbalanced data
CIML 6-6.1
6 02 Mar Beyond binary classification (imbalanced data & multiclass) CIML -6.2

07 Mar
CIML 1 -6, Lectures 1 - 11, All HW, Projects

09 Mar Collective Classification

14 Mar

16 Mar
 Linear Models
CIML 7-7.4

21 Mar
Spring Break

23 Mar
Spring Break

7 28 Mar Linear models and gradient descent CIML 7

Lagrange Multipliers

30 Mar Probabilistic Models
8 04 Apr Naive Bayes modelsCIML 9
9 06 Apr Linear SVM
CIML 7.5-7.7

11 Apr Neural networks I CIML 10-10.3
10 13 Apr Neural networks II
CIML 10.4-10.6

Practice Problems

18 Apr Principal Components
CIML 15.2

20 Aprl
Kernels CIML 11-11.3
11 25 Apr SVM II

27 Apr Deep learning - I
CIML - 10 plus web
12 2 May Deep Learning - II

4 May Bias and Fairness
13 8 May Wrap Up

11 May Practice
Practice Problems