• INI
  • Courses
  • Seminar From Biological to Artificial Neural Networks

Seminar From Biological to Artificial Neural Networks


Artificial neural networks were not only inspired by the brain, but were created in an effort to understand and model the functioning of the brain. In this seminar, we will read and discuss historic scientific articles that track the development of neural networks from the 1940s to the present. Specific topics include

  • McCulloch-Pitts Neurons/ Boolean networks
  • Perceptron
  • Hubel and Wiesel
  • NeoCognitron
  • Convolutional Neural Networks
  • Hopfield
  • Reservoir Computing
  • LSTM
  • RBM
  • NetTalk
  • AlexNet

Learning Outcomes:

After successful completion of this seminar, students will be able to

  • read and understand scientific articles in neural network research
  • know in which situations neural networks are applied
  • understand and discuss the advantages and disadvantages of specific neural networks
  • understand the historical development of neural networks
  • present the results of research in neural networks to an audience


Oral Presentation



Course type
Summer Term 2024


Solid knowledge of calculus, linear algebra, and statistics are required, e.g. Mathematik 1 und 2, Statistik. Knowledge of artificial neural networks.

Students should have taken the class “ A rtificial Neural Networks” , or something equivalent, before enrolling in this seminar.


The articles will be announced in the first meeting.
Background reading: “Neural Networks and Deep Learning” by Charu C. Aggarwal, Springer

The Institut für Neuroinformatik (INI) is a central research unit of the Ruhr-Universität Bochum. We aim to understand the fundamental principles through which organisms generate behavior and cognition while linked to their environments through sensory systems and while acting in those environments through effector systems. Inspired by our insights into such natural cognitive systems, we seek new solutions to problems of information processing in artificial cognitive systems. We draw from a variety of disciplines that include experimental approaches from psychology and neurophysiology as well as theoretical approaches from physics, mathematics, electrical engineering and applied computer science, in particular machine learning, artificial intelligence, and computer vision.

Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany

Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210