Introduction to Deep Learning (Sommersemester 2023)

Lecturer: Prof. Dr. Christoph Lippert (Digital Health - Machine Learning) , Eshant English (Digital Health - Machine Learning) , Wei-Cheng Lai (Digital Health - Machine Learning) , Hadya Sa´Ad Abdalwadoud Yassin (Digital Health - Machine Learning) , Arkadiusz Kwasigroch (Digital Health - Machine Learning)

General Information

• Weekly Hours: 4
• Credits: 6
• Graded: yes
• Enrolment Deadline: 01.04.2023 - 30.04.2023
• Examination time §9 (4) BAMA-O: 28.06.2023
• Teaching Form: Lecture / Seminar
• Enrolment Type: Compulsory Elective Module
• Course Language: English

Programs, Module Groups & Modules

Description

Please note the lecture rooms for the first week

• on 18th April - Raum G2.U.10/14 (Poolraum)
• on 19th April - L-1.06
• Please bring your laptop, if it is possible

This course is designed to give students an in-depth introduction to deep learning and review the state of the art in important applications, such as computer vision and language modeling. The lectures and exercises are designed around fundamentals and use cases and will use real-world data to gain practical experience with machine learning models and algorithms. The course will start with an introduction to the basic concepts of machine learning and empirical data analysis, such as model fitting, selection and validation. During the second part of the course, we will discuss supervised machine learning, starting with linear models, to non-linear models, including deep neural networks, convolutional neural networks and sequence models.  During the third part of the course, we will discuss unsupervised learning, generative models and self-supervision.

Due to significant overlap in course material, this course cannot be combined with the Machine Learning for Precision Medicine from Summer Semester 2019 and neither with the Introduction to Deep Learning Course from Summer Semester 2020.

Learning Objectives:

• Understand concepts, methods and algorithms in machine learning
• Ability to empirically analyze real-world data
• Ability to assess the quality and validity of a machine learning model for a given analysis
• Ability to select, develop, implement and apply appropriate machine learning models and algorithms for a given use case.

Requirements

Maths prerequisites: Linear Algebra (vectors, matrices), Calculus (derivatives), Probabilities (we will refresh them in the first tutorial)

Programming prerequisites: Beginner level in python, syntax (functions, loops, etc.) and its libraries numpy and pandas.

Literature

This course will be based on the material provided at http://d2l.ai/

Learning

Online tools include

• Zoom for Meetings
• HPI Moodle course:https://moodle.hpi.de/course/view.php?id=423
  • If you are not an HPI-student, you can get a Moodle guest account by contacting dhc-lab(at)hpi.de.
  • You do not need an HPI guest account or anything else HPI-specific!
  • For further questions, please consult the teaching team directly.

Examination

• Processing regular Math exercise sheets
• Programming project assignment in teams of 4-5 people during the second half of the course: Code + Final report (40% of final grade)
• Final exam (60% of final grade)

Dates

First lecture: 18th of April -Room G2.U10/14 (Pool Room/Basement)
First Tutorial Session: 19th of April- L1.06

Please bring your laptop, if it is possible!

• Lecture Q&A:  Tuesdays, 17:00 -18:30pm
• Tutorial: Wednesdays  9:15 -10:45 am

It's recommended that students watch the lecture videos for the week before that week's tutorial session.

HPI Moodle https://moodle.hpi.de/course/view.php?id=423

If you have questions or problems, please contact teaching-lippert(at)hpi.de

written exam: 28 June 2023,  09:15 am

Zurück