DS 4440 — Modern Neural Networks
4 semester hoursUndergraduateLectureNUpath ADusually offered: fall, springtypical days: T/FBostonTraditional
Presents a hands-on introduction to modern neural network (deep learning) methods and tools. Covers fundamentals of neural networks, including stochastic gradient descent and backpropagation. Introduces standard and new architectures from simple feedforward networks to generative recurrent and state-of-the-art transformer architectures. Emphasizes using these technologies in practice, via modern toolkits. Reviews applications of these models to various types of data, including images and text.
Prerequisites
- DS 4400 (min D-)
Offering history
| Term | Sections | Enrolled | Capacity | Full | Open seats/section |
|---|---|---|---|---|---|
| Spring 2024 | 1 | 51 | 60 | 85% | 9.0 |
| Fall 2024 | 1 | 8 | 40 | 20% | 32.0 |
| Spring 2025 | 1 | 49 | 51 | 96% | 2.0 |
| Fall 2025 | 1 | 29 | 34 | 85% | 5.0 |
| Spring 2026 | 1 | 74 | 75 | 99% | 1.0 |
Snapshots from scheduled scrapes — not live seat availability. "Full" can exceed 100% when sections over-enroll.
Meeting times
Share of recent sections by weekday: M 18% · T 82% · W 18% · Th 0% · F 58%
Common patterns: TF (58% of sections), T (24% of sections), MW (18% of sections) — in patterns, R means Thursday
Professors
Fall
- Wengong Jin (78% of students) · reviews
- Byron Wallace (22% of students) · reviews
Spring
- Wengong Jin (43% of students) · reviews
- David Bau (29% of students) · reviews
- Steve Schmidt (28% of students) · reviews
Percentages are each professor's average share of the season's enrolled students in recent terms.
Links
Official catalog (DS course descriptions) · Student reviews on RateMyHusky · All DS courses · Plan it at numap.app