Bio-Inspired Modeling & Learning Systems
Introduction - Research and Teaching
We are concerned with design and development of adaptive systems for industrial and business applications, based on our expertise on machine learning, (recurrent) neural networks and bio-inspired algorithms as well as different simulation methods. A central speciality of our group is the development and research on complex (i.e. multi-methodical) forecasting systems. The polysemy of the term «LEARNING SYSTEMS» is an inherent element of the group’s spirit. Our self-concept as a team is the concept of a learning system. We are keen to learn more about new methods and more about ourselves in research and teaching. We are involved in teaching at Bachelor’s and Master’s level as well as continuing education and we actively work on the development of novel teaching methods to learn for our students and together with our students.
Research Topics & Expertise
«Intelligence is based on learning.»
Expertise
- Bio-inspired algorithms and neural networks
- Human in the loop machine learning
- Modeling of complex systems
- Self-learning systems for real world applications
- Forecasting methodologies
Topics
Our Team
Reference Projects
Current publications
-
Frick, Thomas; Glüge, Stefan; Rahimi, Abbas; Benini, Luca; Brunschwiler, Thomas,
2021.
Explainable deep learning for medical time series data [Paper].
In:
Wireless Mobile Communication and Healthcare.
International Conference on Wireless Mobile Communication and Healthcare (MobiHealth), Online, 18 December 2020.
Cham:
Springer.
S.244-256.
Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering ; 362.
Verfügbar unter: https://doi.org/10.1007/978-3-030-70569-5_15
-
Uwate, Yoko; Nishio, Yoshifumi; Ott, Thomas,
2021.
Synchronization of chaotic circuits with stochastically-coupled network topology.
International Journal of Bifurcation and Chaos.
31(01),
S.2150015.
Verfügbar unter: https://doi.org/10.1142/S0218127421500152
-
Uwate, Yoko; Schüle, Martin; Ott, Thomas; Noshio, Yoshifumi,
2020.
Echo state network with chaos noise for time series prediction [Paper].
In:
Proceedings of the 2020 International Symposium on Nonlinear Theory and its Applications.
International Symposium on Nonlinear Theory and its Applications (NOLTA), Okinawa, Japan, 16–19 November 2020.
S.274.
-
2020.
The collaborative learning cellular automata density classification problem [Paper].
In:
Proceedings of the 2020 International Symposium on Nonlinear Theory and its Applications.
International Symposium on Nonlinear Theory and its Applications (NOLTA), Okinawa, Japan, 16–19 November 2020.
S.268.
-
Miniussi, Myriam; Ott, Thomas; Fellermann, Harold,
2020.
Impact of noise and network size in coupled maps with asymmetric influence amplification [Paper].
In:
Proceedings of the NOLTA 2020 Conference.
2020 International Symposium on Nonlinear Theory and Its Applications (NOLTA2020), Online Conference, 16-19 November 2020.
S.282-285.
Current projects
- Seite 01
- Seite 02
- Seite 03
- Seite 04
- Seite 05
- Nächste Seite
-
Klassifikation von Drohnensignalen
Mikrodrohnen haben längst ihren Einzug in die Consumerwelt gefunden und werden immer erschwinglicher und einfacher in der Bedienung. Eine für Consumerdrohnen sehr vielversprechender Technik zur Erfassung ist die Detektion der ausgesendeten Funksignale. Mittels Deep Learning mit künstlichen neuronalen Netzwerken ...
-
Detektion von Drohnensignalen
Mikrodrohnen haben längst ihren Einzug in die Consumerwelt gefunden und werden immer erschwinglicher und einfacher in der Bedienung. Eine für Consumerdrohnen sehr vielversprechender Technik zur Erfassung ist die Detektion der ausgesendeten Funksignale. Mittels Deep Learning mit künstlichen neuronalen Netzwerken ...