Spring 2027

Probability and Information Theory in Machine Learning

Probability and Information Theory in Machine Learning covers probabilistic tools, classification, regression, and information theory concepts like entropy and mutual information.

no offering record for this termCredits unavailable
Recorded instructors · Spring 2027 No instructors listed

Summary

1 / 6

Past student reviews · John Gubner

Three tricky exams containing four to five questions each determined 60% of the final grade.

What you’ll be able to do

  • Identify how ambiguity and noise leads to the need for probabilistic methods in machine learning

  • Implement classification, prediction and generative algorithms using a variety of techniques based in probability, information theory and machine learning

  • Prove optimality of a variety of algorithms and demonstrate understanding of sample complexity bounds

Source: UW Guide 1 UW Guide 2

Grade history

↗
average GPA
letter grades
A
AB
B
BC
C
D
F

All recorded terms · compare terms & instructors

Prerequisites

Course map

(MATH 320, 340, 341, 375, orM E/​COMP SCI/​E C E 532 or concur enroll) and (E C E 331,STAT/​MATH 309, 431,STAT 311, 324, 424,MATH 531, or M E 424 prior to Fall 2026), grad/profsnl standing, or decl in Capstone Cert in Computer Sciences for Professionals

COMPSCI/ECE 561

This is a best-effort interpretation; check the catalog requirements above.

Prerequisite text tree

Professors

Spring 2027

No instructors recorded for this selection.

Historical instructors & teaching patterns

JOHN GUBNER is recorded teaching in Fall 2023. Recorded history may be incomplete and does not establish a future schedule.

Recorded history may be incomplete and does not establish a future schedule.

Calendar & sections

Spring 2027

Schedule loads here as you scroll.

SectionModeEnrolled / capacityWaitlist

Times are Central. Select a meeting for details; export includes recorded dates for the selected sections.

Meeting source records

No records available.

Student experience

the class

Past student reviews · John Gubner

John Gubner's course was described as highly knowledgeable but difficult to follow, with lectures assuming prior familiarity with the material.

Recent recorded grades — Fall 2022: 3.62 GPA, 76.6% A/AB (n=47 letter grades); Fall 2023: 3.40 GPA, 61.7% A/AB (n=47 letter grades); Fall 2024: 3.96 GPA, 97.5% A/AB (n=40 letter grades).

difficulty & workload

Past student reviews · John Gubner

Three tricky exams containing four to five questions each determined 60% of the final grade.

Past student reviews · John Gubner

The reviewer found the course needlessly stressful due to logistics, but noted that Gubner curved grades well and believed most students received high marks.

Topics

  • Classification, regression, probability theory, decision theory, and information quantification.
  • Naive Bayes, probabilistic graphical models, discriminant analysis, logistic regression, EM, source coding, and variational inference.

Skills

  • Classification, regression, probability theory, decision theory, and information quantification using entropy metrics.
  • Advanced ML methods including naive Bayes, probabilistic graphical models, discriminant analysis, and variational inference.
  • Proving algorithm optimality and analyzing sample complexity bounds.

Grades

Latest available · Fall 2024— not enough history to project Spring 2027.

average GPA
A / AB grades
letter grades
Instructor

Grade distribution · % of letter grades

A
AB
B
BC
C
D
F

Grades over time

Through Fall 2024

More grade details Grade mix, volume & source data

Where this course fits relative to

Latest available grades · Fall 2024 · all course levels

GPA

Higher than % of other courses in this group.

Course GPAs · red marks this course’s range

letter grades

More recorded grades than % of other courses in this group.

Typical course in this group: letter grades.

About this comparison

1330 courses over the same term, each with at least 30 recorded letter grades. Cross-listed courses count once. GPA is not a measure of difficulty or teaching quality. The typical course is the median by recorded grade count; tied values are not counted as lower. Grade counts describe course scale, not unique students or typical section size.

Descriptions compare GPA with this group’s average: at least 0.20 higher or lower; otherwise close to average. Section size uses median recorded enrollment: small up to 30, mid-sized 31–99, large 100+. Lectures and discussion/lab sections are described separately.

Sources & history

UW–Madison

Catalog & offerings

Descriptions, prerequisites, and recorded course offerings.

Catalog observation history

Observations at scan time; dates do not imply when a catalog change took effect.

Download part 1
Selected offering source records

No offering records for the selected term.

Raw records 
[]
Rate My Professors

Student reviews

Original comments behind the course and instructor summaries.

Read original reviews
Download part 1
Madgrades

Grade history

Recorded grade distributions by term, section, and instructor.

Explore recorded grades
Dataset & model

Recorded 2026-10-14

View the dataset on Hugging Face
Model outputs & technical records
Qwen/Qwen3.8-27B
LLM outputs across runs
Download part 1
Full model traces

Recorded model configuration, reasoning, and tool conversations.

Download part 1
Model & dataset provenance 
{
  "model": "Qwen/Qwen3.8-27B",
  "model_revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
  "task_version": "17",
  "output_id": "db8f225b28612ec2d2f84f60c576e41f2cff37554d0cb6012b60f89df96109ab",
  "requirements_status": "needs_review",
  "dataset_revision": "fc1811fa52e581ea57a35c0cf3343f8740a8ffbf",
  "observed_at": "2026-10-14 17:50:09.728220+00:00"
}