CMSC 678 --- Introduction to Machine Learning

5/6/19 Assignment 6 is available. It's due 5/14/19 by 11:59 PM.
4/24/19 Assignment 5 is available. Read the short version to get the high-level tasks, but be sure to read the fully detailed version. It's due 5/3/19 by 11:59 PM.
4/10/19 Assignment 4 is available. Read the short version to get the high-level tasks, but be sure to read the fully detailed version. It's due 4/23/19 by 11:59 PM.
3/27/19 Assignment 3 is due 3/29/19 by 11:59 PM.
3/9/19 Assignment 3 is available. Read the short version to get the high-level tasks, but be sure to read the fully detailed version. It's 3/29/19 by 11:59 PM (originally 3/29/19 by 11:59 AM).
2/19/19 Due to the campus closure on 2/20/19, Assignment 2 is now due 3/1/19 by 11:59 AM.
2/12/19 Assignment 2 is available. Read the short version to get the high-level tasks, but be sure to read the fully detailed version. It's now due 3/1/19 by 11:59 AM (originally 2/27/19).
2/10/19 The Course Project is available. It has two milestones due 3/6/19 and 4/17/19; the final due date is 5/22/19.
1/31/19 The submission site is online. To use it, you must be logged in with your UMBC credentials.
1/28/19 Assignment 1 is available. It's due 2/8/19 by 11:59 AM.
1/28/19 The syllabus is available.
1/28/19 See the Piazza discussion board for class announcements and Q&A.

Check out the syllabus for all this information, including policies on academic honesty, accomodations, and late assignments.

Meeting Times: Sondheim, 103
Monday & Wednesday, 2:30pm - 3:45pm
Instructor: Frank Ferraro
ferraro [at] umbc [dot] edu
ITE 358
Monday 3:45 - 4:30
Tuesday 11:00 - 11:30
by appointment
TA: Caroline Kery
ckery1 [at] umbc [dot] edu
ITE 349
Monday 1:00 - 2:00
Thursday 4:00 - 5:00

Topics

The topics covered will include, but are not limited to:

perceptrons
regression (linear, logistic, and non-linear)
spectral, clustering, and dimensionality reduction techniques
support vector machines and kernel methods
neural networks, including deep learning, recurrent neural networks, and convolutional neural networks
Bayesian networks and probabilistic graphical models
clustering
evaluation methodologies and experiment design.

Goals

After taking this course, you will

be introduced to some of the core problems and solutions of ML;
learn different ways that success and progress can be measured in ML;
be exposed to how these problems relate to those in statistics, artificial intelligence, and specialized areas of ML (such as natural language processing and computer vision);
have experience implementing a number of ML programs;
read and analyze research papers;
practice your (written) communication skills.

The following schedule of topics is subject to change.

Legend:

ESL: Elements of Statistical Learning: https://web.stanford.edu/~hastie/ElemStatLearn/printings/ESLII_print12.pdf
ITILA: Information Theory, Inference and Learning Algorithms: http://www.inference.phy.cam.ac.uk/itprnn/book.pdf
UML: Understanding Machine Learning: From Theory to Algorithms: http://www.cs.huji.ac.il/~shais/UnderstandingMachineLearning/
CIML: A Course in Machine Learning: http://ciml.info/

Date	Topic	Main Reading: Read All	Advanced Reading: Optionally Read Some	Assignment Out	Assignment Due
Monday, 1/28	Introduction: what is ML?	ESL Ch 1	ESL Ch 2	A1: Math & Programming Review	—
Wednesday, 1/30	Probability, loss functions, and decision theory	CIML Ch 2 if in need of a probability refresh: ITILA Ch 2	UML Ch 2 UML Ch 14 ITILA Ch 36	—	—
Monday, 2/4	- Linear regression, classification, and perceptrons (+more on gradient optimization)	CIML Ch 7 (linear models) CIML Ch 4 (perceptrons)	ESL Ch 3 UML Ch 9.2	—	—
Wednesday, 2/6				—	—
Friday, 2/8				—	due: A1
Monday, 2/11				Course Project A2: Loss Functions and Multiclass Classification	—
Wednesday, 2/13	Experimental Setup, Multi-class vs. Multi-label Classification, and Evaluation Logistic regression/maxent models	CIML Ch 9.5-9.7 ESL Ch 4.4	UML Ch 9.3 ITILA Ch 39, 41.1-41.3	—	—
Monday, 2/18		CIML Ch 9.5-9.7 ESL Ch 4.4	UML Ch 9.3 ITILA Ch 39, 41.1-41.3	—	—
Wednesday, 2/20	Neural networks, backpropagation, & autodifferentiation	CIML Ch 10 Goodfellow et al. (2016), Ch 6 (Deep Feedforward Networks)	ESL Ch 11 UML Ch 20 ITILA Ch 38-39	—	—
Monday, 2/25	Neural networks, backpropagation, & autodifferentiation		ESL Ch 11 UML Ch 20 ITILA Ch 38-39	—	—
Wednesday 2/27	Recurrent & convolutional neural networks	Goodfellow et al. (2016), Ch 11 (Practical Methodology)	Goodfellow et al. (2016), Ch 9 (CNNs) Goodfellow et al. (2016), Ch 10 (RNNs)	—	—
Friday, 3/1	—	—	—	—	due: A2
Monday, 3/11	Midterm Review	—	—	—	—
Wednesday, 3/13	Midterm;	—	—	—	—
Monday, 4/8; Wednesday 4/10	Dimensionality Reduction: Linear Discriminant Analysis & Principal Component Analysis	CIML Ch 15.2	ESL Ch 4.3 ESL Ch 14.5-14.10 UML Ch 23, 24.3	A4: Neural Networks	—
Monday, 4/15; Wednesday 4/17	Prototype vs. exemplar learning: k-means and k-nearest neighbor	CIML Ch 15.1	ESL Ch 13, 14.3 UML Ch 22 ITILA Ch 20	—	—
Monday, 4/22	Kernel methods & Support vector machines	CIML Ch 11 (Kernel + SVM), 7.7 (SVM)	ESL Ch 6 (Kernel) UML Ch 16 (Kernel) ESL Ch 12 (SVM) UML Ch 15 (SVM)	—	—
Monday, 4/29	Expectation Maximization & Probabilistic Modeling	CIML Ch 16	ESL Ch 8.5 UML Ch 24.0-24.1 (Maximum likelihood) UML Ch 24.4 (EM) ITILA Ch 20	—	—
Wednesday, 5/1	Expectation Maximization & Probabilistic Modeling	CIML Ch 16		—	—
Monday, 5/6	Graphical Models	ITILA Ch 16 (Message Passing, e.g., for forward-backward) CIML Ch 9	ITILA Ch 25 and 26 (~16 pages) ESL Ch 17 (excluding 17.3.2, 17.4.2-end; ~17 pages) ESL Ch 17 (excluding 17.3.2, 17.4.2-end; ~17 pages)	—	—
Wednesday, 5/8	Graphical Models	—		—
Monday, 5/13	Overview of Decision Trees, Ensemble Methods, and Reinforcement Learning Course Overview	CIML Ch 1 (Decision Trees) CIML Ch 13 (Ensemble Methods)	—	—	—

Introduction to Machine Learning

Spring 2019 — CMSC 678