Simulating Dynamic Plastic Continuous Neural Networks by Finite Elements

• Published in: IEEE transaction on neural networks and learning systems Vol. 25; no. 8; pp. 1583 - 1587
• Main Authors: Joghataie, Abdolreza, Torghabehi, Omid Oliyan
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.2014; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Action Potentials - physiology; Animals; Applied sciences; Artificial intelligence; Biological neural networks; Biomimetics - methods; Computer science; control theory; systems; Computer Simulation; Connectionism. Neural networks; Dynamical systems; Exact sciences and technology; Finite element; Finite Element Analysis; Finite element method; Humans; Mathematical analysis; Mathematical models; Models, Neurological; Nerve Net - physiology; Neural networks; Neural Networks (Computer); Neurons; Neurons - physiology; Nonlinear dynamics; numerical modeling; Plastics; Strain; Stress; Training; wave propagation; wave propagation; neural networks; Finite element; numerical modeling; Input output; Delay control; Continuous function; Neural network; Modeling; Weight; Finite element method; Information processing; Continuous medium; Rectangular plate; Properties of materials; Non linear effect; Localization; Plastics; Dynamic model
• ISSN: 2162-237X; 2162-2388
• DOI: 10.1109/TNNLS.2013.2294315

We introduce dynamic plastic continuous neural network (DPCNN), which is comprised of neurons distributed in a nonlinear plastic medium where wire-like connections of neural networks are replaced with the continuous medium. We use finite element method to model the dynamic phenomenon of information processing within the DPCNNs. During the training, instead of weights, the properties of the continuous material at its different locations and some properties of neurons are modified. Input and output can be vectors and/or continuous functions over lines and/or areas. Delay and feedback from neurons to themselves and from outputs occur in the DPCNNs. We model a simple form of the DPCNN where the medium is a rectangular plate of bilinear material, and the neurons continuously fire a signal, which is a function of the horizontal displacement.