Deep Learning 1

6 EC

Semester 1, period 2

52041DEL6Y

Owner Master Artificial Intelligence
Coordinator dr. Y.M. Asano
Part of Master Artificial Intelligence, Master Logic,

Course manual 2022/2023

Objectives

  • The students can explain and motivate the fundamental principles and mechanisms behind Deep Learning’s past present and future
  • The students can explain the major challenges, directions and active domains of research in the field of deep learning along with their advantages and disadvantages
  • The student can program, train and run deep learning models in a server environment and, in doing so, effectively leverage existing open-source code
  • The student is able to debug and critically assess deep learning methods from a practical-engineering, and mathematical-theoretic point of view.
  • The student can tackle new deep learning problems with well-reasoned combinations of existing approaches and in so doing effectively learn from vast resources available on the internet

Teaching methods

  • Lecture
  • Laptop seminar
  • Self-study
  • Seminar

The main goal of the lecture is to introduce new materials and show the connection of the principles and methods with current research.

The goal of the practical sessions is to get the student working independently and become proficient in programming for deep learning.

Learning activities

Activity

Hours

Hoorcollege

28

Tentamen

2.5

Werkcollege

28

Self study

110

Total

168

(6 EC x 28 uur)

Attendance

This programme does not have requirements concerning attendance (OER part B).

Additional requirements for this course:

This programme does not have requirements concerning attendance (OER part B).

Assessment

Item and weight Details

Final grade

3 (50%)

Tentamen

Mandatory

1 (17%)

Assignment 1

1 (17%)

Assignment 2

1 (17%)

Assignment 3

The final grade will be an average of assignment and exam grades.
Students pass the course if the average is >=5.5+ , but the exam grade must be >=5.0. If it is below 5.0, the student may take the resit exam, which will replace the grade of the original exam and will be further averaged with the assignments' grades.
Assignment deadlines are as outlined, late hand-ins are not accepted.

Inspection of assessed work

Piazza will be kept open for discussions. The ANS platform will be open to the students for discussions once their works are graded.

Assignments

Assignment 1 Multilayer Perceptrons, Backpropagation, 
Assignment 2 Pretrained models, ViTs, Prompt-learning
Assignment 3 Generative Models 

Fraud and plagiarism

The 'Regulations governing fraud and plagiarism for UvA students' applies to this course. This will be monitored carefully. Upon suspicion of fraud or plagiarism the Examinations Board of the programme will be informed. For the 'Regulations governing fraud and plagiarism for UvA students' see: www.student.uva.nl

Course structure

Week Topics Material Deadlines
1 (1.Nov)

Introduction to Deep Learning
Feedforward Neural Networks

Textbooks:
Deep Learning (Chapters 1, 6, 7-7.5)

Understanding Deep Learning (Ch 1.1 -  1.2.1.2, 4, 7-7.3)

 
2 (8.Nov) Deep Learning Optimisation

Textbooks:
Deep Learning (Ch 7.8, 8)
Understanding Deep Learning (Ch 6, 9-9.3.3)

 
3 (15.Nov)

Convolutional Neural Networks
Modern Convolutional Networks

Textbooks:
Deep Learning (Chapter 9)
Understanding Deep Learning (Ch 10, 11)

18.11: Deadline Assignment 1*
*extension, see Canvas announcement
4 (22.Nov)

Transformers
Graph Neural Networks

Textbooks:
UDL book (Ch 12, 13)
"Attention is all you need" by Vaswani et al. 
Dive into DL (Ch 11)
"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges" by Bronstein et al. (Ch 1, 2, 3, 5.1, 5.3)

  
5 (29.Nov)

Generative Adversarial Networks
Generative Modelling
Deep Variational Inference

Textbooks:
Deep Learning (Chapter 19, 20)
"Auto-Encoding Variational Bayes" by Kingma & Welling

2.12. Deadline Assignment 2
6 (6. Dec)

 

Neural learning of 3D (Guest Lecture)
Deep Learning for solving physics (Guest Lecture)

Papers:
"NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis" by Mildenhall et al.
Tbd

10.12. Deadline Assignment 3
7 (13. Dec) Self-supervised and Multi-modal Learning

Papers:
"Self-labelling via simultaneous clustering and representation learning" by Asano et al.
"Self-supervised object detection from audio-visual correspondence" by Afouras et al.
Tbd

  
8 Questions & Answers, Exam Exam at 19th December  

Timetable

The schedule for this course is published on DataNose.

Contact information

Coordinator

  • dr. Y.M. Asano

Staff