2023-Spring-CSE151A-Introduction to Machine Learning and CSE 251A-ML: Learning Algorithms

Undergraduate Class and Graduate Class, CSE, UCSD, 2023

Class Time: Tuesdays and Thursdays, 9:30AM to 10:50AM. Room: WLH 2001. Piazza: piazza.com/ucsd/spring2023/cse151a.

Online Lecturing for First Week

To offer waitlist students opportunities to learn more about this course, in the first week, we deliver the lecture over Zoom: https://ucsd.zoom.us/j/93540989128. The lectures will be recorded.

Overview

This course mainly focuses on introducing machine learning methods and models that are useful in analyzing real-world data. It will cover classical regression & classification models, clustering methods, and deep neural networks. No previous background in machine learning is required, but all participants should be comfortable with programming, and with basic optimization and linear algebra.

There is no textbook required, but here are some recommended readings:

Prerequisites

  1. Ability to code in Python: functions, control structures, string handling, arrays and dictionaries.

  2. Familiarity with basic probability, at the level of CSE 21 or CSE 103.

  3. Familiarity with basic linear algebra, at the level of Math 18 or Math 20F.

Co-scheduling: CSE 151A and CSE 251A

  • CSE 151A and CSE 251A are co-scheduled in Spring’23. These two courses will share the same lectures.
  • The most difficult course materials will be optional for 151A while required for 251A.
  • The HW and Midterm will be more challenging for CSE 251A.
  • The Piazza forum is shared.

TAs and Tutors

  • Teaching Assistants:

    • CSE 251A TAs
      • Danlu Chen (dac013 AT ucsd.edu)
      • Chengyu Dong (cdong AT ucsd.edu)
      • Dheeraj Mekala (dmekala AT ucsd.edu)
      • Yufan Zhuang (y5zhuang AT ucsd.edu)
    • CSE 151A TAs
      • Weitang Liu (wel022 AT ucsd.edu)
      • Zilong Wang (ziw049 AT ucsd.edu)
      • Zihan Wang (ziw224 AT ucsd.edu)
      • Xiyuan Zhang (xiz032 AT ucsd.edu)

Office Hours

Note: all times are in Pacific Time.

Grading

  • Homework: 15% each. Your lowest (of five) homework grades is dropped (or one homework can be skipped).
  • Midterm: 40%.
  • You should complete all work individually.
  • Late submissions are NOT accepted.

Lecture Schedule

Recording Note: Please download the recording video for the full length. Dropbox website will only show you the first one hour.

HW Note: All HWs due before the lecture time 9:30 AM PT in the morning.

(the schedule is tentative)

WeekDateTopic & SlidesEvents
104/04 (Tue)Introduction: Concepts and EvaluationsHW1 out
104/06 (Thu)A Geometric View of Linear Algebra 
204/11 (Tue)Nearest Neighbor ClassificationHW1 due
204/13 (Thu)Gradients and OptimizationHW2 out
304/18 (Tue)Least-Squares Regression, Logistic Regression, and Perceptron 
304/20 (Thu)Overfitting and Regularization 
404/25 (Tue)Support Vector Machine (SVM) 
404/27 (Thu)SVM: Duality and KernelHW2 due, HW3 out
505/02 (Tue)K-Means Clustering & its Variants 
505/04 (Thu)“Soft” Clustering: Gaussian Mixture 
605/09 (Tue)Principle Component Analysis 
605/11 (Thu)Midterm (no class, take-home, 24-hour) 
705/16 (Tue)Naive Bayes and Decision Tree 
705/18 (Thu)Ensemble Learning: Bagging and BoostingHW3 due, HW4 out
805/23 (Tue)Multi-class Classification & Feed-foward Neural Networks 
805/25 (Thu)Convolutional Neural Networks 
905/30 (Tue)Bias-Variance in Deep Neural NetworksHW4 due, HW5 out
906/01 (Thu)Semi-supervised and Weakly-supervised Learning 
1006/06 (Tue)Learning with Noisy/Biased Data 
1006/08 (Thu)Large Language ModelsHW5 due

Homework (60%)

Your lowest (of five) homework grades is dropped (or one homework can be skipped).

  • HW1: Concepts and Evaluations (15%). 151A HW1 251A HW1 This homework mainly focuses on the machine learning concepts and how to evaluate different tasks.
  • HW2: KNN and Linear Models (15%). 151A HW2 251A HW2 This homework mainly focuses on nearest neighbor, least-square regression, logistic regression, and regularization.
  • HW3: SVM and Clustering (15%). 151A HW3 251A HW3 This homework mainly focuses on support vector machine, k-means, Gaussian Mixture, and PCA.
  • HW4: Ensemble Learning (15%). 151A HW4 251A HW4 This homework mainly focuses on decision tree, random forest, and AdaBoost.
  • HW5: Neural Networks (15%). 151A HW5 251A HW5 This homework mainly focuses on implementation of some simple neural networks.

Midterm (40%)

It is an open-book, take-home exam, which covers all lectures given before the Midterm. Most of the questions will be open-ended. Some of them might be slightly more difficult than homework. You will have 24 hours to complete the midterm, which is expected for about 2 hours.

  • Start: May 11, 9:30 AM PT
  • End: May 12, 9:30 AM PT
  • Midterm problems download: 151A 251A
  • Please make your submissions on Gradescope.