Abstract
In this chapter, nodes are now implemented using both a global node number and a vector address giving us address based graph models. Here, the vector address is a six dimensional one with each entry being an integer. Hence, a neural module has a six dimensional address that states explicitly what its position in the neural circuit is; i.e. it is a node in the right brain, visual cortex, can 4, OCOS 3, FFP 3 and Layer 2/3 3. All of the MatLab codes are then rewritten to use addresses. This requires the ability to move seamlessly from the address of a node and it global node number and vice versa. Hence, all backward and forward node information sets must come in two flavors: addresses and global numbers. All of this is worked out along with appropriate training code.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this chapter
Cite this chapter
Peterson, J.K. (2016). Address Based Graphs. In: BioInformation Processing. Cognitive Science and Technology. Springer, Singapore. https://doi.org/10.1007/978-981-287-871-7_19
Download citation
DOI: https://doi.org/10.1007/978-981-287-871-7_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-287-869-4
Online ISBN: 978-981-287-871-7
eBook Packages: EngineeringEngineering (R0)