Display language
To modulepage Generate PDF

#41071 / #1

Seit WiSe 2022/23

English

Deep Learning 1

6

Montavon, Gregoire

benotet

Schriftliche Prüfung

Zugehörigkeit


Fakultät IV

Institut für Softwaretechnik und Theoretische Informatik

34352000 FG Maschinelles Lernen

No information

Kontakt


MAR 4-1

Montavon, Gregoire

gregoire.montavon@tu-berlin.de

Learning Outcomes

Understanding of the foundations of neural networks and deep learning, including optimization and regularization aspects. Understanding of the most popular deep neural network architectures used in practice (e.g. convolutional neural networks). Ability to implement a neural network using common deep learning frameworks.

Content

Foundations of neural networks, including the perceptron, multi-layer perceptrons, activation functions, loss functions, error backpropagation, and the questions of optimization and regularization. Common optimization techniques such as SGD, momentum, and RMSProp. Common regularization techniques such as weight decay, dropout, and Lipschitz constraints. Presentation of popular architectures, such as the convolutional neural network, autoencoders, and recurrent neural networks. Introduction to the PyTorch deep learning framework.

Module Components

Pflichtgruppe:

All Courses are mandatory.

Course NameTypeNumberCycleLanguageSWSVZ
Deep Learning 1 - mainIVWiSeEnglish4

Workload and Credit Points

Deep Learning 1 - main (IV):

Workload descriptionMultiplierHoursTotal
Concepts & Theory10.06.0h60.0h
Exercises10.06.0h60.0h
Programming10.06.0h60.0h
180.0h(~6 LP)
The Workload of the module sums up to 180.0 Hours. Therefore the module contains 6 Credits.

Description of Teaching and Learning Methods

The module will consist of weekly lectures accompanied with weekly homeworks.

Requirements for participation and examination

Desirable prerequisites for participation in the courses:

There are no formal prerequisites. However, prior knowledge of multivariate calculus and Python programming will be assumed. Basic knowledge of machine learning is also desirable.

Mandatory requirements for the module test application:

1. Requirement
Unbenoteter Übungsschein

Module completion

Grading

graded

Type of exam

Written exam

Language

English

Duration/Extent

120 minutes

Duration of the Module

The following number of semesters is estimated for taking and completing the module:
1 Semester.

This module may be commenced in the following semesters:
Wintersemester.

Maximum Number of Participants

This module is not limited to a number of students.

Registration Procedures

cf. course webpage

Recommended reading, Lecture notes

Lecture notes

Availability:  unavailable

 

Electronical lecture notes

Availability:  unavailable

 

Literature

Recommended literature
No recommended literature given

Assigned Degree Programs


This module is used in the following Degree Programs (new System):

Studiengang / StuPOStuPOsVerwendungenErste VerwendungLetzte Verwendung
Computational Engineering Science (Informationstechnik im Maschinenwesen) (M. Sc.)13SoSe 2023SoSe 2024
Computer Engineering (M. Sc.)112WiSe 2022/23SoSe 2024
Computer Science (Informatik) (M. Sc.)116WiSe 2022/23SoSe 2024
Elektrotechnik (M. Sc.)18WiSe 2022/23SoSe 2024
Information Systems Management (Wirtschaftsinformatik) (M. Sc.)14WiSe 2022/23SoSe 2024

Miscellaneous

No information