ECE-685D
INTRO TO DEEP LEARNING
Offered Fall 2026
Term
Overview
Feedback is mixed. The clearest upside is that some students still find real value in the course. Best for students who can handle a demanding pace without needing constant hand-holding.
DepartmentELEC&CMP
Terms offeredFall
Typical enrollment79–116
Semesters of data3
7.5
Hrs / week
117
Responses
292
Enrollment
40%
Response Rate
Evaluation Scores
Overall quality
Teaching, content, and experience combined.
4.0
Intellectually stimulating
Challenges students to think deeply.
4.3
Instructor effectiveness
Explains concepts and facilitates learning.
4.2
Difficulty
Higher means harder.
4.1
Feedback Analysis
Feedback Analysishigh
Analysis based on student evaluations
Based on 138 comments across 3 sections
Feedback is mixed. The clearest upside is that some students still find real value in the course. Best for students who can handle a demanding pace without needing constant hand-holding.
Student Reports
How hard is the A?
Hard to get an A
Students repeatedly frame high grades as something you have to earn. This reads as hard to ace rather than casually easy, especially once the course pace or grading standards ramp up.
Homework Load
Heavy homework load
Homework load is one of the clearest friction points. Students repeatedly describe assignments, readings, or problem sets as time-consuming.
Lecture Load
Lighter lecture burden
Student comments describe this as more discussion-, seminar-, or workshop-driven than lecture-dependent. The lecture burden itself does not sound like the main source of friction.
Strengths
• Instructor ratings are strong even when the comments do not cluster around one obvious positive theme.
Tradeoffs
• Difficulty runs high even when comments do not settle on one dominant complaint.
Best fit for
Best for students who can handle a demanding pace without needing constant hand-holding.
Watch out for
• A large share of the evidence comes from one instructor's version of the course, so this may not generalize cleanly.
Student Responses
1. how to build deep learning models 2. how to write better python codes 3. how to use GenAI
Fall 2024 · Tarokh, Vahid
I could consider my class uptake in three ways: 1) I had no idea about generative models, and generative modeling in general. The class had an emphasis on it, and the instructor did a good job in teaching them. 2) The mathematics of different deep learning approaches was explored desirably. 3) A good variety of applications and advancements was also discussed.
Fall 2024 · Tarokh, Vahid
Programming of Neural Networks in Python using PyTorch. Knowledge about implementation and concepts of topics in the domain of deep learning. More sophisticated optimization methods.
Fall 2024 · Tarokh, Vahid
I did not understand anything in the lectures. The slides were complicated and without explaination of equations. Had to rely fully on youtube to learn the material.
Fall 2024 · Tarokh, Vahid
In this course, I learned to build and train neural networks, understand the math behind deep learning models, and use PyTorch for tasks like Computer vision and NLP.
Fall 2024 · Tarokh, Vahid
Rating History
Rating history
Error bars show \u00B11 std dev
| Term | Instructor | Overall | Difficulty | Hrs/wk | Enrolled |
|---|---|---|---|---|---|
| Fall 2025 | Tarokh, Vahid 1.5Rate My ProfessorsQuality1.5Difficulty4.5Would retake0%Based on 2 ratingsClick to view on RMP → | — | — | 6.8 | 116 |
| Fall 2024 | Tarokh, Vahid 1.5Rate My ProfessorsQuality1.5Difficulty4.5Would retake0%Based on 2 ratingsClick to view on RMP → | 3.9 | 4.1 | 7.5 | 97 |
| Fall 2023 | Tarokh, Vahid 1.5Rate My ProfessorsQuality1.5Difficulty4.5Would retake0%Based on 2 ratingsClick to view on RMP → | 4.0 | 4.2 | 8.1 | 79 |
Instructor
Tarokh, VahidELEC&CMP
Also teaches
ECE-689 ADV TOPICS IN DEEP LEARNING4.5