Evolution of bilateral symmetry in agents controlled by spiking neural networks
We present in this paper three novel developmental models allowing information to be encoded in space and time, using spiking neurons placed on a 2D substrate. In two of these models, we introduce neural development that can use bilateral symmetry. We show that these models can create neural controllers for agents evolved to perform chemotaxis. Neural bilateral symmetry can be evolved and be beneficial for an agent. This work is the first, as far as we know, to present developmental models where spiking neurons are generated in space and where bilateral symmetry can be evolved and proved to be beneficial in this context.
Item Type | Other |
---|---|
Date Deposited | 26 Jul 2024 23:06 |
Last Modified | 26 Jul 2024 23:06 |
-
picture_as_pdf - 903562.pdf
Explore Further
Read more research from the creator(s):
Find work associated with the faculties and division(s):
- School of Computer Science
- Science & Technology Research Institute
- Centre for Computer Science and Informatics Research
- Department of Computer Science
- School of Physics, Engineering & Computer Science
- Centre of Data Innovation Research
- Centre for Future Societies Research
Find other related resources: