Artificial grammar recognition using two spiking neural networks
-
1
Malardalen University, IDT, Sweden
-
2
F.C. Donders Centre for Cognitive Neuroimaging, Netherlands
Introduction:A biologically inspired neocortical model consisting of spiking neurons is designed to perform artificial grammar processing. Building on work in [1] the model is designed to categorize symbol strings as belonging to a Reber grammar [2]. Columnar organization of the cortex is used as the general inspiration of the network [3,4].
Each node is a minicolumn model consisting of 100 neurons; of which 80 are excitatory and 20 inhibitory. Excitatory connections inside the node sustain activity. The nodes are designed to sustain the activity for 1000 ms after the node received input. After that time local inhibition overcomes excitatory activity silencing the node.
Two network topologies were compared in this project. One consists of a complete set of nodes representing every bi-gram and tri-gram producible by the grammar. The nodes are configured in a hierarchy with the substring length increasing by one symbol with higher levels. Feed forward connections are used to propagate activity between layers. The other network consists of a minimized number of nodes which represent states in the finite state machine (FSM) defining the grammar. This, minimized network, maintains a higher level of activity but performs comparably to the complete network. In this network nodes are re-used to represent multiple substrings.
The minimized network demonstrates the spiking neural networks ability to store and extract complex information with a small number of nodes.
Discussion:The performance of the two networks investigated here supports the feasibility of artificial grammar recognition using spiking neural networks. Future work will benefit from collaboration with experimentation of the same recognition task in clinical trials.
References
1. Petersson KM et al.: Artificial grammar learning and neural networks. Proc. Cogn. Sci. Soc. 2005, pp. 1726-1731.
2. Reber, AS: Implicit learning of artificial grammar. J. Verb. Learn. & Verb. Behav. 1967, 6, 855-863.
3. Çürüklü B: A Canonical Model of the Primary Visual Cortex. Mälardalen University Press, 2005
4. Mountcastle VB: The columnar organization of the neocortex. Brain 1997, :701-722.
5. Gewaltig MO and Diesmann M: NEST. Scholarpedia 2007, 2(4):1430
Conference:
Neuroinformatics 2009, Pilsen, Czechia, 6 Sep - 8 Sep, 2009.
Presentation Type:
Poster Presentation
Topic:
Computational neuroscience
Citation:
Cavaco
P,
Curuklu
B and
Karl-Petersson
M
(2019). Artificial grammar recognition using two spiking neural networks.
Front. Neuroinform.
Conference Abstract:
Neuroinformatics 2009.
doi: 10.3389/conf.neuro.11.2009.08.096
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
25 May 2009;
Published Online:
09 May 2019.
*
Correspondence:
Philip Cavaco, Malardalen University, IDT, Eskilstuna, Sweden, philip.cavaco@ki.se