course: Artificial Neural Networks

number:
310002
teaching methods:
lecture with tutorials
media:
overhead transparencies, computer based presentation, black board and chalk
responsible person:
Prof. Dr. Sen Cheng
lecturer:
Prof. Dr. Sen Cheng (Neuroinformatik)
language:
english
HWS:
4
CP:
6
offered in:
winter term

dates in winter term

  • start: Monday the 07.10.2019
  • lecture Mondays: from 16:00 to 18.00 o'clock in HNC 30
  • tutorial (alternativ) Wednesdays: from 10:00 to 12.00 o'clock in GD 2/478
  • tutorial (alternativ) Wednesdays: from 16:00 to 18.00 o'clock in ID 03/121
  • tutorial (alternativ) Thursdays: from 10:00 to 12.00 o'clock in IA 1/181
  • tutorial (alternativ) Thursdays: from 14:00 to 16.00 o'clock in SSC 2/148
  • tutorial (alternativ) Thursdays: from 16:00 to 18.00 o'clock in SSC 2/148
  • tutorial (alternativ) Fridays: from 12:00 to 14.00 o'clock in ID 03/139
  • tutorial (alternativ) Fridays: from 16:00 to 18.00 o'clock in ID 03/121

Exam

All statements pertaining to examination modalities (for the summer/winter term of 2020) are given with reservations. Changes due to new requirements from the university will be announced as soon as possible.

Termin wird vom Dozenten bekannt gegeben

Form of exam:written
Registration for exam:FlexNow
Duration:120min

goals

Artificial neural networks (ANN) were inspired by the architecture and function of the brain. Nevertheless, their greatest strength is not that they are good models of the brain, but rather that they are powerful function approximators. Since the 1980's many types of ANN have been developed and tricks for training ANNs on data proliferated. Recent advances in computing hardware and the availability of large datasets has made it possible to train ANNs such that they perform better than humans, e.g., on image recognition. In this class, students will, firstly, gain a theoretical understanding of the principles underlying the methods applied to neural networks and, secondly, learn practical skills in implementing neural networks and applying them for data analysis.

content

  • optimization problems
  • regression
  • logistic regression
  • biological neural networks
  • model selection
  • universal approximation theore
  • perceptron
  • MLP
  • backpropagation
  • deep neural networks
  • recurrent neural networks
  • LSTM
  • Hopfield network
  • Bolzmann machine

requirements

none

recommended knowledge

  • calculus
  • linear algebra
  • statistics
  • programming

literature

  1. Géron, Aurélien "Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques for Building Intelligent Systems", None, None
  2. Aggarwal, Charu C. "Neural Networks and Deep Learning", Springer Verlag, None https://link.springer.com/download/epub/10.1007%2F978-3-319-94463-0.epub

miscellaneous

Please register for the tutorials in advance!

Link to the Moodle course: https://moodle.ruhr-uni-bochum.de/m/enrol/index.php?id=22627