Name
Abstract | ||
|---|---|---|
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. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TNNLS.2013.2294315 | Neural Networks and Learning Systems, IEEE Transactions |
Keywords | Field | DocType |
finite element analysis,neural nets,DPCNN,bilinear material,continuous material,dynamic plastic continuous neural networks,feedback,finite element method,nonlinear plastic medium,wire-like connections,Finite element,neural networks,numerical modeling,wave propagation,wave propagation. | Continuous function,Topology,Information processing,Nonlinear system,Pattern recognition,Computer science,Finite element method,Input/output,Artificial intelligence,Artificial neural network,Bilinear interpolation | Journal |
Volume | Issue | ISSN |
25 | 8 | 2162-237X |
Citations | PageRank | References |
2 | 0.46 | 3 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Abdolreza Joghataie | 1 | 2 | 0.46 |
| Omid Oliyan Torghabehi | 2 | 2 | 0.46 |