The functionality of spatial and time domain artificial neural models
Capanni, Niccolo Francesco
MetadataShow full item record
This thesis investigates the functionality of the units used in connectionist Artificial Intelligence systems. Artificial Neural Networks form the foundation of the research and their units, Artificial Neurons, are first compared with alternative models. This initial work is mainly in the spatial-domain and introduces a new neural model, termed a Taylor Series neuron. This is designed to be flexible enough to assume most mathematical functions. The unit is based on Power Series theory and a specifically implemented Taylor Series neuron is demonstrated. These neurons are of particular usefulness in evolutionary networks as they allow the complexity to increase without adding units. Training is achieved via various traditiona and derived methods based on the Delta Rule, Backpropagation, Genetic Algorithms and associated evolutionary techniques. This new neural unit has been presented as a controllable and more highly functional alternative to previous models. The work on the Taylor Series neuron moved into time-domain behaviour and through the investigation of neural oscillators led to an examination of single-celled intelligence from which the later work developed. Connectionist approaches to Artificial Intelligence are almost always based on Artificial Neural Networks. However, another route towards Parallel Distributed Processing was introduced. This was inspired by the intelligence displayed by single-celled creatures called Protoctists (Protists). A new system based on networks of interacting proteins was introduced. These networks were tested in pattern-recognition and control tasks in the time-domain and proved more flexible than most neuron models. They were trained using a Genetic Algorithm and a derived Backpropagation Algorithm. Termed "Artificial BioChemical Networks" (ABN) they have been presented as an alternative approach to connectionist systems.
Permalink for this recordhttp://hdl.handle.net/10059/241
Collections in which this item appears
Showing items related by title, author, creator and subject.
Gerrard, Claire E.; McCall, John; Macleod, Christopher; Coghill, George M. (Springer. http://dx.doi.org/10.1007/s00500-014-1330-9, 2015-06)GERRARD, C. E., MCCALL, J., MACLEOD, C. and COGHILL, G. M., 2015. Applications and design of cooperative multi-agent ARN-based systems. Soft Computing, 19 (6), pp. 1581-1594.The Artificial Reaction Network (ARN) is an Artificial Chemistry inspired by Cell Signalling Networks (CSNs). Its purpose is to represent chemical circuitry and to explore the computational properties responsible for ...
Gerrard, Claire E.; McCall, John; Coghill, George M.; Macleod, Christopher (Springer. http://dx.doi.org/10.1007/s00500-013-1174-8, 2014-10)GERRARD, C. E., MCCALL, J., COGHILL, G. M. and MACLEOD, C., 2014. Exploring aspects of cell intelligence with artificial reaction networks. Soft Computing, 18 (10), pp. 1899-1912.The Artificial Reaction Network (ARN) is a Cell Signalling Network inspired connectionist representation belonging to the branch of A-Life known as Artificial Chemistry. Its purpose is to represent chemical circuitry ...
Gerrard, Claire E.; McCall, John; Macleod, Christopher; Coghill, George M. (IEEE http://dx.doi.org/10.1109/UKCI.2013.6651281, 2013-09)GERRARD, C. E., MCCALL, J., MACLEOD, C. and COGHILL, G. M., 2013. Combining biochemical network motifs within an ARN-agent control system. In: Y. JIN and S. A. THOMAS, eds. Proceedings of the 13th UK Workshop on Computational Intelligence (UKCI) 2013 9-11 September 2013. New York: IEEE. pp. 8-15.The Artificial Reaction Network (ARN) is an Artificial Chemistry representation inspired by cell signaling networks. The ARN has previously been applied to the simulation of the chemotaxis pathway of Escherichia coli and ...