DATASCI 315 Fall 2024

Statistics and Artificial Intelligence

Overview | Course Calendar | Lecture Schedule

Overview

Statistical concepts are increasingly integrated into artificial intelligence applications, which often draw on a large amount of data received, transmitted, and generated by computers or networks of computers. This course introduces students to statistics and machine learning techniques such as deep neural networks, with applications to text and image data.

At the end of this course, students will be familiar with the deep learning paradigm, and will be able to analyze data using different classes of deep learning models. The course gives an introduction to the basics of deep neural networks, and their applications to various AI tasks.

Syllabus

For course policies, course requirements, and grading policies, please see the syllabus [link].

Piazza

Students should sign up Piazza [link] to join course discussions.

All communications with the teaching team (the instructor and the GSIs) should be conducted over Piazza; please do not email. If you'd like to reach the instructor or the GSIs for private questions, please post a private note on Piazza that is only visible to the instructor and the GSIs. See here for detailed instructions. The GSIs and the instructor will be monitoring piazza, endorsing correct student answers, and answering questions that remain after a discussion.

As a bonus, up to 3 percentage points will be added to your final course grade based on piazza participation. You will get (3x/100) bonus percentage points if the number of your total Piazza contributions is (x * 100)% of the maximum number of contributions among all students. The number of Piazza contributions will be determined by Piazza class statistics.

Teaching Team, Office Hours, and Labs

  • Instructor: Yixin Wang
  • GSI:
    • Sahana Rayan (Office Hours: Wed 10-11:30am, Thurs 10-11:30am, in-person)
    • Jacob Trauger (Office Hours: Mon 12-3pm, in-person)
    • Andrej Leban (Office Hours: Wed 3-4pm, in-person; Tue 10-11am, Fri 12-1pm online)
    In person GSI Office Hours: Angell Hall G219
    Virtual GSI Office Hours: https://umich.zoom.us/j/4489857771 (passcode: 115588)
    Please refer to course calendar for office hour details.
    • The website for the labs are here.

    Course Calendar

    • Lecture: Tue/Thur 8:30am-9:50am
    • Location: 1210 CHEM
    • Google Calendar: The Google Calendar below ideally contains all events and deadlines for student's convenience. Please feel free to add this calendar to your Google Calendar by clicking on the plus (+) button on the bottom right corner of the calendar below. Any adhoc changes to the schedule will be visible on the calendar first.

    Lecture Schedule

    The Schedule is subject to change.

    DLPy = Deep Learning with Python (2nd edition) by Chollet
    DL = Deep Learning by Goodfellow, Bengio and Courville [link]
    NNDL = Neural Networks and Deep Learning by Nielsen [link]
    D2L = Dive into Deep Learning by Zhang, Lipton, Li and Smola [link]

    Date Topic Readings

    Lecture 1

    08/27

    Introduction

    DLPy What is deep learning?, Chap. 1
    DL Introduction, Chap. 1
    D2L Introduction, Chap. 1

    Lecture 2

    08/29

    Vectorization and Linear Algebra Bootcamp I

    D2L Geometry and Linear Algebraic Operations, Sec. 22.1.1-9

    Lecture 3

    09/03

    Vectorization and Linear Algebra Bootcamp II

    ''

    Lecture 4

    09/05

    Regression as Deep Learning I

    D2L Linear Regression, Sec. 3.1.1-4
    D2L Softmax Regression, Sec. 4.1.1
    D2L Loss Function, Sec. 4.1.2

    Lecture 5

    09/10

    Regression as Deep Learning II

    ''

    Lecture 6

    09/12

    Regression as Deep Learning III

    ''

    Lecture 7

    09/17

    Regression as Deep Learning IV

    ''

    Lecture 8

    09/19

    Regression as Deep Learning V

    ''

    Lecture 9

    09/24

    Regression as Deep Learning VI

    ''

    Lecture 10

    09/26

    First Steps with TensorFlow

    DLPy, Sec. 2.4.4
    DLPy, Sec. 3.1-4
    DLPy, Sec. 3.5.1-4

    Lecture 11

    10/01

    Shallow Neural Networks with Keras

    DLPy, Sec. 2.1, Sec. 4.1-3

    Lecture 12

    10/03

    Opening the Black Box of Keras

    ''

    Lecture 13

    10/08

    Getting started with NNs: Classification and Regression I

    DLPy, Sec. 2.1, Sec. 4.1-3

    Lecture 14

    10/10

    Getting started with NNs: Classification and Regression II

    ''

    Fall break

    10/15

    ------------

    ------------

    Lecture 15

    10/17

    Fundamentals of ML I

    DLPy, Sec. 5.1-3, 5.4.4, 6.3

    Lecture 16

    10/22

    Fundamentals of ML II

    ''

    Lecture 17

    10/24

    Midterm Exam

    ------------

    Lecture 18

    10/29

    Convolutional Neural Networks I

    D2L, Sec. 7.1-6
    DLPy, Sec. 7.2

    Lecture 19

    10/31

    Convolutional Neural Networks II

    ''

    Lecture 20

    11/05

    Convolutional Neural Networks III

    ''

    Lecture 21

    11/07

    Convolutional Neural Networks IV

    ''

    Lecture 22

    11/12

    Convolutional Neural Networks V

    ''

    Lecture 23

    11/14

    Deep Learning for Sequence Data I

    DLPy, Sec. 10.2-4

    Lecture 24

    11/19

    Deep Learning for Sequence Data II

    ''

    Lecture 25

    11/21

    Deep Learning for Sequence Data III

    ''

    Lecture 26

    11/26

    Deep Learning for Sequence Data IV

    ''

    Thanksgiving break

    11/28

    ------------

    ------------

    Lecture 27

    12/03

    Deep Generative Modeling

    D2L, Chap. 18

    Lecture 28

    12/05

    Summary (and wiggle room)

    ------------

    Acknowledgements

    The course materials are adapted from the related courses offered by Alexander Amini, Alfredo Canziani, Justin Johnson, Andrew Ng, Bhiksha Raj, Grant Sanderson, Rita Singh, Ava Soleimany, and Ambuj Tewari.