Deep Learning 1

6 EC

Semester 1, period 2

52041DEL6Y

Owner Master Artificial Intelligence
Coordinator dr. X. Zhen PhD
Part of Master Artificial Intelligence,

Course manual 2021/2022

Objectives

  • The students will be taught the fundamentals of deep learning.
  • The students will learn from first principles the latest deep learning models in the state-of-the-art of computer vision and natural language processing.
  • The students will learn to implement the latest models in the state-of-the-art of deep learning models for computer vision and natural language processing problems.
  • Students will to program big deep learning models in servers, a skill required by all in academia and industry.
  • Students will learn what are the most relevant and frequent practical problems in Deep Learning, and how they can be addressed in practice.

Teaching methods

  • Lecture
  • Laptop seminar
  • Self-study
  • Seminar

Learning activities

Activity

Hours

Hoorcollege

28

Tentamen

2

Werkcollege

28

Self study

110

Total

168

(6 EC x 28 uur)

Attendance

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

Assessment

Item and weight Details

Final grade

1 (100%)

Tentamen

Students pass for the course if the average is 5.5+ . In case students fail for the exam (<5), the resit fully determines the final grade. The final grade will be an average of assignment and exam grades.  

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

The assignments and individual and will be assessed as a part of the final grade.

Assignment 1  Multilayer Perceptron and Backpropagation
Assignment 2  CNNs, RNNs and GNNs
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 number Subjects Studiestof
1

Introduction to Deep Learning

Feedforward Neural Networks

Textbooks:

Deep Learning (Chapters 1, 6)

Probabilistic Machine Learning An Introduction (Chapter 13)
2 Deep Learning Optimisation

Textbooks:

Deep Learning (Chapter 8)

Probabilistic Machine Learning An Introduction (Chapter 8)
3

Convolutional Neural Networks

Modern Convolutional Networks

Textbooks:

Deep Learning (Chapter 9)

Probabilistic Machine Learning An Introduction (Chapter 14)
4

Recurrent Neural Networks

Graph Neural Networks (Guest lecture)

Textbooks:

Deep Learning (Chapter 10)

Probabilistic Machine Learning An Introduction (Chapter 15, 23)
5

Attention and Transformers

Generative Adversarial Networks

Textbooks:

Deep Learning (Chapter 20)

Probabilistic Machine Learning An Introduction (Chapter 15)
6

Deep Variational Inference

Deep Learning Generalisation (Guest lecture)

Textbooks:

Deep Learning (Chapter 20)

Probabilistic Machine Learning

Advanced Topics (Chapter 21, 22)
7 Meta-Learning

Textbooks:

Probabilistic Machine Learning

Advanced Topics (Chapter 20)
8 Question and Answer, Exam  

Timetable

The schedule for this course is published on DataNose.

Contact information

Coordinator

  • dr. X. Zhen PhD

Staff

  • C. Athanasiadis
  • I.A. Auzina MSc
  • L.F. Bereska MSc
  • Jim Boelrijk
  • Natasha Butt
  • Mohammad Derakhshani MSc
  • Winfried van den Dool MSc
  • Y. Du MSc
  • Alex Gabel MSc
  • M. Hendriksen
  • Tom Lieberum
  • Phillip Lippe MSc
  • J. Liu MSc
  • Yongtuo Liu MSc
  • B.K. Miller MSc
  • I. Najdenkoska
  • Nadja Rutsch
  • S. Salehidehnavi MSc
  • J. Shen MSc
  • T.J. van Sonsbeek
  • R. Valperga MSc
  • H. Wang MSc
  • Zehao Xiao