Introduction to Machine Learning : CSE 474/574

Instructor : Dr. Sreyasee Das Bhattacharjee

Email : sreyasee@buffalo.edu
Office: Davis Hall 349
Office Hours: Fri 400pm – 500pm and By Appointment

General Information

Lecture Times: M W F, 12:40 PM - 1.30 PM

TA(s):

Course Prequisites: Expertise in Python, good familiarity with Calculus, Linear Algebra, and Data Structures.

Course Overview:

  1. To provide a broad survey of approaches and techniques in ML
  2. To understand the concept of the topics in depth along with the mathematical formulations designed to propose them.
  3. To develop the design and implementation skills that will help you to build intelligent, adaptive artifacts
  4. We will use Python to discuss the implementation part of the concepts. However, you are free to use any other programming language if you feel at home with it. At the end of every topic, we will discuss a ‘ready to run code’ and walk ourselves through it. Students are expected to run it along with the class discussion.

Piazza : We will use Piazza to answer questions and post announcements about the course. Please sign up here. 

Grade Composition :       Programming Assignment: 20%
                          Written Assignments: 20%
                          Mid-term(s): 20%
                          Final: 20%
                          Class Quizzes: 15%
                          Class and Weekly Discussion Forum Participation: 5%

Textbook/Refrence Books:

  • Machine Learning: a Probabilistic Perspective, by Kevin Murphy (2012).
  • Pattern Recognition and Machine Learning, by Chris Bishop (2006).
  • Introduction to Machine Learning, Third Edition, by Ethem Alpaydin (2015)
    • Other topic specific references will be added in Piazza. The soft-copies of the books are available in UBlearn. The reading materials for each topic will be mentioned in the class and also in the lecture slides.

    Rough Course Schedule (each topic will take up 1-3 weeks)

    1. Introduction and Probability Overview (week 1).
    2. Linear Models (≈ 2.5 weeks): This will include Logistic Regression/Perceptrons, Support Vector Machine (SVM).
    3. Non-linear Models (≈ 2 weeks): This will include Non-linear Regularization, Neural Network.
    4. Kernel Methods (≈ 1 week):Multi Kernel Regression, Kernel SVM.
    5. Graphical Models (≈ 2 weeks): Bayesian Networks, MRV, Inference in Graphical Models
    6. Deep Learning (≈ 1 weeks)
    7. Unsupervised Learning (≈ 1.5 weeks): Clustering, Dimension Reduction
    8. Reinforcement Learning (≈ 1 week)
    9. Sequencial Model (≈ 2 week): Markov Property, HMM, Generalization of HMM, RNN<10.Ensemble Methods (≈ 1 week)/li>
    10. Ensemble Methods (≈ 1 week)
    11. Ethical Issues of AI, Trustworthy & Explainable AI (≈ 1 week)

    Academic Integrity:
    (Short) Don’t cheat! You will be caught and punished. Our department is serious about graduating ethical and upstanding computer scientists. The policy has recently been updated and will be enforced.
    (Long) All academic work must be your own. Plagiarism, defined as copying or receiving materials from a source or sources and submitting this material as one’s own without acknowledging the particular debts to the source (quotations, paraphrases, basic ideas), or otherwise representing the work of another as one’s own, is never allowed. Collaboration, usually evidenced by unjustifiable similarity, is never permitted in individual assignments. Any submitted academic work may be subject to screening by software programs designed to detect evidence of plagiarism or collaboration. Also, do not post any of the course material outside of the Course piazza page. It will be interpreted as an attempt to get non-approved help. For more info :
    UB CSE Academic Integrity

    Working with others: Please do help each other! This material is fun, but can be challenging. Discussing it with peers can deepen your understanding. You can talk about the homework problems and ways of approaching them, however, every person must write up solutions and code separately. We will compare all submissions with each other AND non-approved sources. I you can find something online, so we can we.

    Special Accommodations: In case of need of special accommodations please go the following link for more information.
    Special Accommodations.