Spring 2027

Machine Learning

Explores computational approaches to learning, covering inductive inference, connectionism, formal models, algorithm comparison, and cognitive modeling.

offering recorded3 credits
Recorded instructors · Spring 2027 Fred Sala4.3/5

Summary

1 / 6

Past student reviews · Mark Craven

Programming assignments covered around 60% of the grade, complementing the mostly theoretical nature of the course material.

What you’ll be able to do

  • Identify different aspects of machine learning, including supervised learning, unsupervised learning, and reinforcement learning

  • Implement and analyze a variety of supervised models for classification and regression, including decision trees, instance-based models, naive Bayes, support vector machines, a variety of neural networks, linear and logistic regression, and others

  • Implement and analyze neural network models, starting with the perceptron, and continuing to multilayer perceptrons, convolutional neural networks, recurrent neural networks, along with deep generative models

  • Identify various types of regularization techniques and their properties

  • Implement optimization techniques used in modern machine learning, including gradient descent and stochastic gradient descent

  • Apply various concepts and metrics involved in evaluating models: accuracy, F measures, ROC, and precision/recall curves, and implement cross-validation

  • Analyze unsupervised learning techniques for clustering, dimensionality reduction, and latent models

  • Identify classical and modern techniques to improve models or deal with dearth of data: ensemble methods, semi-supervised learning, weak supervision

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

Graduate/professional standing

  • Graduate/professional standing
COMPSCI/ECE 760 used by

“Used by” includes alternatives; linked courses may have other requirements. This is a best-effort interpretation; check the catalog requirements above.

Prerequisite text tree
  • Graduate/professional standing

Professors

Spring 2027

Fred Sala

Adjusted rating
RMP difficulty
captured reviews
About this rating

Raw average: 4.72/5 from 32 quality ratings. The adjusted rating blends this with the UW review average (3.66/5), weighted as 20 additional ratings. Smaller samples stay closer to that average. Each captured review is counted once in the prior; this does not correct who chooses to leave a review.

RMP profile ↗ · All captured review dates; profile matched by name.

Recent recorded grades — Fall 2021: 3.78 GPA, 91.8% A/AB (n=98 letter grades). Includes jointly taught sections.

Historical instructors & teaching patterns

FRED SALA is recorded teaching in Fall 2021. Recorded history may be incomplete and does not establish a future schedule.

MARK CRAVEN is recorded teaching in Fall 2012, Fall 2013, Fall 2014, Fall 2015, Fall 2016, Spring 2018, Spring 2019. Recorded history may be incomplete and does not establish a future schedule.

YINGYU LIANG is recorded teaching in Fall 2017, Fall 2018, Spring 2020. 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
LEC 001Classroom Instruction0 / 1500
LEC 001Classroom Instruction0 / 650

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

Meeting source records
Download part 1

Student experience

the class

Past student reviews · Mark Craven

Students described the course content as excellent, noting that the slides made tough concepts easy to understand while maintaining a theoretical focus.

Recent recorded grades — Spring 2025: 3.58 GPA, 89.4% A/AB (n=66 letter grades); Fall 2025: 3.80 GPA, 98.1% A/AB (n=105 letter grades); Spring 2026: 3.61 GPA, 79.3% A/AB (n=58 letter grades).

difficulty & workload

Past student reviews · Mark Craven

Programming assignments covered around 60% of the grade, complementing the mostly theoretical nature of the course material.

Past student reviews · Yingyu Liang

One student found the final project topics amazing and appreciated the instructor's willingness to brainstorm research ideas on hot topics like reinforcement learning.

Topics

  • Inductive inference, explanation-based learning, analogical learning, and connectionism
  • Supervised, unsupervised, and reinforcement learning paradigms
  • Cognitive modeling and related psychological findings

Skills

  • Implementing and analyzing neural network architectures including CNNs and RNNs
  • Applying optimization techniques like gradient descent and stochastic gradient descent
  • Analyzing unsupervised learning methods such as clustering and dimensionality reduction

Grades

Historical instructor

Spring 2027 · Projected

Before grades are released

– average GPA

Approximate 80% prediction interval

About this estimate

The course’s semester-average GPA, not an individual student’s grade. The center uses 5 same-season terms, weighted toward recent results.

The range uses the finite-sample 80th-percentile rank of absolute errors from earlier same-season forecasts. Each forecast uses only records from earlier terms. At least four forecasts are required; bounds are rounded outward and limited to 0–4. This is an empirical estimate: changing instructors or grading policies can reduce its coverage.

8 earlier forecasts · 0.10 GPA average error.

Grades over time

Through Spring 2027

More grade details Grade mix, volume & source data

Where this course fits relative to

Latest available grades · Spring 2026 · 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

1280 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
COMPSCI/ECE 760 · Spring 2027

Machine Learning

Recorded 2026-10-14
COMPSCI/ECE 760 · Spring 2027

Machine Learning

Recorded 2026-10-14
Raw records 
[
  {
    "run_id": "20261014T203208-0851c9a1",
    "semester": "1274",
    "observed_at": "2026-10-14 17:50:09.728220+00:00",
    "offering_id": "1274:266:004331",
    "course_id": "COMPSCI/ECE 760",
    "course_uid": "course_821f9bd2b5a7758dd5db1e18",
    "term_id": "1274",
    "source_course_id": "004331",
    "source_subject_id": "266",
    "title": "Machine Learning",
    "credits_min": 3,
    "credits_max": 3,
    "typically_offered": "Occasionally"
  },
  {
    "run_id": "20261014T203208-0851c9a1",
    "semester": "1274",
    "observed_at": "2026-10-14 17:50:09.728220+00:00",
    "offering_id": "1274:320:004331",
    "course_id": "COMPSCI/ECE 760",
    "course_uid": "course_821f9bd2b5a7758dd5db1e18",
    "term_id": "1274",
    "source_course_id": "004331",
    "source_subject_id": "320",
    "title": "Machine Learning",
    "credits_min": 3,
    "credits_max": 3,
    "typically_offered": "Occasionally"
  }
]
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 1Download part 2
Model & dataset provenance 
{
  "model": "Qwen/Qwen3.8-27B",
  "model_revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
  "task_version": "17",
  "output_id": "be7eaa6434e4c0824122a467ba572f342ff521391f949d405d462f07355533ef",
  "requirements_status": "valid",
  "dataset_revision": "fc1811fa52e581ea57a35c0cf3343f8740a8ffbf",
  "observed_at": "2026-10-14 17:50:09.728220+00:00"
}