700.390 (23S) Deep Learning and Spiking Neural Networks for Advanced Data Mining

Sommersemester 2023

Anmeldefrist abgelaufen.

Erster Termin der LV
19.05.2023 09:00 - 17:00 Online Off Campus
... keine weiteren Termine bekannt

Überblick

Lehrende/r
LV-Titel englisch Deep Learning and Spiking Neural Networks for Advanced Data Mining
LV-Art Vorlesung-Kurs (prüfungsimmanente LV )
LV-Modell Präsenzlehrveranstaltung
Semesterstunde/n 2.0
ECTS-Anrechnungspunkte 4.0
Anmeldungen 8 (20 max.)
Organisationseinheit
Unterrichtssprache Englisch
LV-Beginn 19.05.2023
eLearning zum Moodle-Kurs

Zeit und Ort

Liste der Termine wird geladen...

LV-Beschreibung

Intendierte Lernergebnisse

Neural networks, deep learning (DL), and computational neuroscience have different applications in text categorization, e.g., spam filtering, fraud detection, optical character recognition, machine vision, e.g., face detection, licenses plate recognition, advanced driver assistance systems, natural-language processing, e.g., spoken language understanding, market segmentation, e.g., predict if a customer will get a credit, and bioinformatics, e.g.,  classify proteins or lipidomes according to their function. The material covered in this course expands upon what was covered in course  700.395, which is titled  Data Mining and Neurocomputing.  The following are examples of methods that will be covered:

  •     The principles of artificial neural networks (NN),
  •     Convolutional neural networks  (CNN),
  •     Recurrent neural networks (RNN),
  •     Generative models, e.g., autoencoders, variational autoencoders, generative adversarial network (GAN).

The theoretical foundations of the approaches that will be explored in the class will place a strong emphasis on application and modeling techniques using different datasets. The result of the learning is a solid understanding of deep learning fundamentals. The lecture will guide to transferring of the acquired knowledge to solve classification problems for industry and research, (c) the basics of computational neuroscience, and (d) show some use-cases and exciting applications from the state-of-the-art.

Lehrmethodik

Lectures

classroom exercises, quiz and activities.

Evaluation

Project 50% + Quiz (20%) + Assignments (20%) + Class activity (10%)

Inhalt/e

  • Data preprocessing / data augmentation
  • Unsupervised Learning and Clustering
  • Deep Learning (multilayer perceptron, convolutional models, recurrent models)
  • Time series forecast (long-short-term-memory and gated recurrent units)
  • Spiking neural networks
  • Deep learning libraries (torch, theano, keras, tensorflow...etc.)
  • Evaluation Metrics

Erwartete Vorkenntnisse

Desirable prerequisites:

  1. Calculus
  2. Linear algebra
  3. Coding skills in python

Literatur

Ian Goodfellow, Yoshua Bengio, Aaron Courville, Deep Learning, MIT Press, 2016.

  • ISBN-13: 978-0262035613 
  • ISBN-10: 0262035618

Prüfungsinformationen

Im Fall von online durchgeführten Prüfungen sind die Standards zu beachten, die die technischen Geräte der Studierenden erfüllen müssen, um an diesen Prüfungen teilnehmen zu können.

Beurteilungsschema

Note Benotungsschema

Position im Curriculum

  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Information and Communications Engineering: Supplements (NC, ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (Anhang 4) ( 0.0h VK, VO, KU / 14.0 ECTS)
        • 700.390 Deep Learning and Spiking Neural Networks for Advanced Data Mining (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Information and Communications Engineering: Supplements (NC, ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (Anhang 4) ( 0.0h VK, VO, KU / 14.0 ECTS)
        • 700.390 Deep Learning and Spiking Neural Networks for Advanced Data Mining (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 15W.1)
    • Fach: Autonomous Systems and Robotics: Advanced (ASR) (Wahlfach)
      • Wahl aus dem LV-Katalog (siehe Anhang 3) ( 0.0h VK, VO / 30.0 ECTS)
        • 700.390 Deep Learning and Spiking Neural Networks for Advanced Data Mining (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 22W.1)
    • Fach: Information and Communicatons Enginnering: Supplements (Wahlfach)
      • 1.3b Ausgewählte Lehrveranstaltungen (siehe Curriculum Seite 16) ( 0.0h VC, KS / 14.0 ECTS)
        • 700.390 Deep Learning and Spiking Neural Networks for Advanced Data Mining (2.0h VC / 4.0 ECTS)
  • Masterstudium Information and Communications Engineering (ICE) (SKZ: 488, Version: 22W.1)
    • Fach: ICE- Supplements (Wahlfach)
      • 2.3b Ausgewählte Lehrveranstaltungen (siehe Curriculum Seite 18) ( 0.0h VC, KS / 14.0 ECTS)
        • 700.390 Deep Learning and Spiking Neural Networks for Advanced Data Mining (2.0h VC / 4.0 ECTS)

Gleichwertige Lehrveranstaltungen im Sinne der Prüfungsantrittszählung

Diese Lehrveranstaltung ist keiner Kette zugeordnet