Exercise: Neural networks and deep learning (Inf-NNDL) (080071)- Dozentinnen/Dozenten
- Dr.-Ing. Claudius Zelenka, Prof. Dr. Carsten Meyer
- Angaben
- Übung, 2 SWS
Unterrichtssprache Englisch
Zeit und Ort: Fr 12:15 - 13:45, LMS8 - R.EG.016 (40), LMS8 - R.EG.010 (26); Einzeltermin am 14.4.2023 12:15 - 13:45, OHP2 - Otto-Hahn-Hörsaal
vom 14.4.2023 bis zum 7.7.2023
Bemerkung zu Zeit und Ort: Exercises are on a weekly basis
- Voraussetzungen / Organisatorisches
- Students are encouraged to bring their own laptops to the laboratory exercises.
- Inhalt
- Practical exericses in neural networks and deep learning on basis of Python
- Zusätzliche Informationen
- Erwartete Teilnehmerzahl: 70
- Zugeordnet zu: Inf-NNDL: Neural networks and deep learning (080049)
Inf-NNDL: Neural networks and deep learning (Inf-NNDL) (080049)- Dozent/in
- Prof. Dr. Carsten Meyer
- Angaben
- Vorlesung, 2 SWS, ECTS-Studium, ECTS-Credits: 6
Unterrichtssprache Englisch, Further information can be found on Moodle.
Zeit und Ort: jede 2. Woche Fr 10:00 - 11:30, OHP2 - Otto-Hahn-Hörsaal; jede 2. Woche Fr 14:00 - 15:30, CAP2 - Hörsaal F
vom 14.4.2023 bis zum 7.7.2023
1. Prüfungstermin (Klausur am Ende der Vorlesungszeit eines Semesters): 11.7.2023, 10:00 - 12:00 Uhr, Raum OHP5 - [Chemie II]
2. Prüfungstermin (Klausur zu Beginn der Vorlesungszeit des Folgesemesters): 9.10.2023, 10:00 - 12:30 Uhr, Raum LMS6 - R.11
Klausureinsicht: 23.10.2023, 11:30 - 12:30 Uhr, Raum CAP4 - R.1110
Bemerkung zu Zeit und Ort: lectures are every 2nd week
- Voraussetzungen / Organisatorisches
- Mathematical basics of algebra and analysis and of optimization.
Students are encouraged to bring their own laptops to the laboratory exercises; knowledge of the python programming language is encouraged, but not a prerequisite. Exercises are encouraged to be solved in student teams.
- Inhalt
- Neural Networks and Deep Learning recently have gained strong interest (Deep Learning has been considered one of 10 breakthrough technologies by the MIT Technology Review 2013). The aim of the course is to provide a fundamental understanding of important concepts, algorithms, techniques and architectures of neural networks and deep learning.
After completing the course, students should
have a basic overview over neural network and deep learning concepts, algorithms and architectures, suitable applications, capabilities and limitations,
be able to apply suitable neural network and deep learning techniques to new problems,
analyze the outcome of neural network and deep learning experiments and explore potential methods to improve performance.
- Biological basis (neuron and networks)
- Artificial neuron models
- Artificial neural networks: Architectures and the learning problem
- Feedforward neural networks, multi-layer perceptron
- Learning in neural networks and the backpropagation algorithm
- Deep Learning: Motivation and concepts
- Convolutional neural networks
- (If time permits:) Recurrent neural networks: Long Short Term Memory (LSTM)
- (If time permits:) Unsupervised learning: Autoencoders
- (If time permits:) Generative models: Variational Autoencoder, Generative Adversarial Networks
- Empfohlene Literatur
- Ian Goodfellow et al., "Deep Learning", MIT Press, 2016
Michael Nielsen: "Neural Networks and Deep Learning", 2017
(More literature in the course)
- Zusätzliche Informationen
- Erwartete Teilnehmerzahl: 70
- Zugeordnete Lehrveranstaltungen
- UE: Exercise: Neural networks and deep learning (080071)
-
Dozentinnen/Dozenten: Dr.-Ing. Claudius Zelenka, Prof. Dr. Carsten Meyer
Zeit und Ort: Fr 12:15 - 13:45, LMS8 - R.EG.016 (40), LMS8 - R.EG.010 (26); Einzeltermin am 14.4.2023 12:15 - 13:45, OHP2 - Otto-Hahn-Hörsaal; Bemerkung zu Zeit und Ort: Exercises are on a weekly basis
|
|
