Skip to main content
Fall 2026

DS 6050: Deep Learning

A 12-module graduate training camp for building deep-learning systems from first principles, diagnosing why they fail, and making defensible engineering and research decisions.

Download PDF

Instructor

Heman Shakeri, PhD

hs9hd@virginia.edu

Teaching assistant

Fokhrul Islam

UVA ID: sdh4py

Delivery

Weekly live lectures

Weekly lectures and readings on Canvas

Canonical reading

Deep Learning: Making It Learnable

Open course book

Course purpose

Move beyond surface-level recipes

Grand challenges in medical imaging, language, and scientific discovery require more than off-the-shelf code. They require quantitative understanding, disciplined implementation practice, and the judgment to evaluate trade-offs honestly.

By the end of the course, you should be able to reason from mathematical principles, build core components from scratch, debug model behavior systematically, and adapt those learning strategies to new architectures and research after graduation.

Three learning phases

01
Modules 1–3
Foundations & From-Scratch Understanding

Build the mathematical foundation, then implement linear models, multilayer perceptrons, and backpropagation from scratch with NumPy. Optimization and ablation methodology become recurring tools rather than one-off topics.

02
Modules 4–9
Architectural Innovations & Domain Specialization

Connect data modality to architecture: CNNs for spatial data, RNNs for sequences, and attention and Transformers for general-purpose modeling. Diagnose the training challenges specific to each family.

03
Modules 10–12
Modern Practice & Research Skills

Study large-scale pretraining, vision transformers, efficient adaptation, and generative modeling while practicing paper reproduction, systematic ablations, and research judgment.

Course calendar

One module per week across the 12-week sequence.

  1. Week 1Module 1
    From Linear Regression to Neural Networks
  2. Week 2Module 2
    Backpropagation
  3. Week 3Module 3
    Training MLPs
  4. Week 4Module 4
    Convolutional Neural Networks
  5. Week 5Module 5
    Advanced CNN Architectures
  6. Week 6Module 6
    Encoder Decoder Architectures
  7. Week 7Module 7
    Recurrent Neural Networks
  8. Week 8Module 8
    Attention Mechanism
  9. Week 9Module 9
    Self-Attention and Transformers
  10. Week 10Module 10
    Transformer Models
  11. Week 11Module 11
    Prompting, PEFT & Quantization
  12. Week 12Module 12
    Generative Modeling

Assessment as learning

Assessment is designed first as guided practice: unit tests, iteration, reflection, feedback, and optional peer code review make evaluation a by-product of learning.

Programming assignments

Homework 1

Modules 1–2
100 points

Foundations & backpropagation

Linear models, gradients, and early autograd practice. The supporting Colab is on Module 1.

Homework 2

Modules 4–5
100 points

Optimization & CNNs

Training stability, convolutional stacks, and transfer learning. The supporting Colab is on Module 5.

Homework 3

Module 7
100 points

Sequence-to-sequence learning

Implement and study a recurrent sequence-to-sequence model in the provided Colab.

Homework 4

Module 8
100 points

Attention

Add cross-attention to a GRU-based sequence-to-sequence model.

Homework 5

Module 10
100 points

Transformer 2.0

Integrate the course's Transformer concepts in the final programming assignment.

Homework policy

One automatic drop, equal weight

Every homework is graded out of 100 points, so all five carry exactly the same weight. Your homework grade is the average of your four highest scores out of five: one homework is dropped for everyone, automatically.

The drop is the skip

A skipped homework is scored 0 and becomes your drop. If you submit all five, your weakest score is dropped. Everyone is graded on four assignments; there is no separate skip plus drop.

Nothing is submitted late

Work not submitted by the deadline is scored 0 and becomes your drop. You do not need to notify us, apologize, or make a request.

Documented exceptions

A second missed homework requires instructor or TA approval before the deadline. If a sudden emergency prevents advance notice, contact us as soon as you are able, with documentation. An approved absence is removed from the calculation, and your automatic drop still applies.

Same benefit for everyone

All five count equally. No homework is worth more than another, and there is nothing to gain by choosing which one to skip.

One skipped

92, 88, 0, 95, 90 → 91.25

All submitted

92, 88, 71, 95, 90 → 91.25

In both examples, the lowest score is removed and the remaining four scores are averaged.

Module quizzes

Short 10–15 question, open-book checks focus on understanding rather than memorization. Full credit is based on thoughtful completion, with immediate explanatory feedback.

Quizzes are delivered in Canvas; quiz questions are not published on the public module pages.

Group grand challenge

Teams apply course concepts to a real problem through three feedback-centered milestones.

  1. 1Proposal & literature review
    5%
  2. 2Mid-project checkpoint
    10%
  3. 3Final deliverables
    25%

Grading

Homework deadlines, the automatic drop, and excused absences follow the homework policy above.

40%

Programming assignments

Five assignments, each out of 100; grade is the average of your four highest scores (one automatic drop)

40%

Group project

Proposal, checkpoint, and final deliverables

20%

Participation

Canvas quizzes and course engagement

Professional and academic integrity

All work must comply with the UVA Honor System. Individual assignments must be original work; conceptual discussion is encouraged, and external code, ideas, and resources must be cited. Include the honor pledge with relevant submissions.