|Publication type:||Conference paper|
|Type of review:||Peer review (publication)|
|Title:||Self-organizing maps of artificial neural classifiers : a brain-like pin factory|
|Proceedings:||Artificial Life and Evolutionary Computation|
|Editors of the parent work:||Schneider, Johannes Josef|
Weyland, Mathias Sebastian
Füchslin, Rudolf Marcel
|Conference details:||XV International Workshop on Artificial Life and Evolutionary Computation (WIVACE), Winterthur, Switzerland, 15-17 September 2021|
|Series:||Communications in Computer and Information Science|
|Publisher / Ed. Institution:||Springer|
|Publisher / Ed. Institution:||Cham|
|Subjects:||Self-organization; Neural network|
|Subject (DDC):||006: Special computer methods|
|Abstract:||Most machine learning algorithms are based on the formulation of an optimization problem using a global loss criterion. The essence of this formulation is a top-down engineering thinking that might have some limitations on the way towards a general artificial intelligence. In contrast, self-organizing maps use cooperative and competitive bottom-up rules to generate low-dimensional representations of complex input data. Following similar rules to SOMs, we develop a self-organization approach for a system of classifiers that combines top-down and bottom-up principles in a machine learning system. We believe that such a combination will overcome the limitations with respect to autonomous learning, robustness and self-repair that exist for pure top-down systems. Here we present a preliminary study using simple subsystems with limited learning capacities. As proof of principle, we study a network of simple artificial neural classifiers on the MNIST data set. Each classifier is able to recognize only one single digit. We demonstrate that upon training, the different classifiers are able to specialize their learning for a particular digit and cluster according to the digits. The entire system is capable of recognizing all digits and demonstrates the feasibility of combining bottom-up and top-down principles to solve a more complex task, while exhibiting strong spontaneous organization and robustness.|
|Fulltext version:||Published version|
|License (according to publishing contract):||Licence according to publishing contract|
|Departement:||Life Sciences and Facility Management|
|Organisational Unit:||Institute of Computational Life Sciences (ICLS)|
|Appears in collections:||Publikationen Life Sciences und Facility Management|
Files in This Item:
There are no files associated with this item.
Show full item record
Vachey, G., & Ott, T. (2022). Self-organizing maps of artificial neural classifiers : a brain-like pin factory [Conference paper]. In J. J. Schneider, M. S. Weyland, D. Flumini, & R. M. Füchslin (Eds.), Artificial Life and Evolutionary Computation (pp. 163–171). Springer. https://doi.org/10.1007/978-3-031-23929-8_16
Vachey, G. and Ott, T. (2022) ‘Self-organizing maps of artificial neural classifiers : a brain-like pin factory’, in J.J. Schneider et al. (eds) Artificial Life and Evolutionary Computation. Cham: Springer, pp. 163–171. Available at: https://doi.org/10.1007/978-3-031-23929-8_16.
G. Vachey and T. Ott, “Self-organizing maps of artificial neural classifiers : a brain-like pin factory,” in Artificial Life and Evolutionary Computation, 2022, pp. 163–171. doi: 10.1007/978-3-031-23929-8_16.
Vachey, Gabriel, and Thomas Ott. “Self-Organizing Maps of Artificial Neural Classifiers : A Brain-like Pin Factory.” Artificial Life and Evolutionary Computation, edited by Johannes Josef Schneider et al., Springer, 2022, pp. 163–71, https://doi.org/10.1007/978-3-031-23929-8_16.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.