Neuroplasticity in dynamic neural networks comprised of neurons attached to adaptive base plate

Joghataie, A ; Sharif University of Technology | 2016

848 Viewed
  1. Type of Document: Article
  2. DOI: 10.1016/j.neunet.2015.11.010
  3. Publisher: Elsevier Ltd , 2016
  4. Abstract:
  5. In this paper, a learning algorithm is developed for Dynamic Plastic Continuous Neural Networks (DPCNNs) to improve their learning of highly nonlinear time dependent problems. A DPCNN is comprised of a base medium, which is nonlinear and plastic, and a number of neurons that are attached to the base by wire-like connections similar to perceptrons. The information is distributed within DPCNNs gradually and through wave propagation mechanism. While a DPCNN is adaptive due to its connection weights, the material properties of its base medium can also be adjusted to improve its learning. The material of the medium is plastic and can contribute to memorizing the history of input-response similar to neuroplasticity in natural brain. The results obtained from numerical simulation of DPCNNs have been encouraging. Nonlinear plastic finite element modeling has been used for numerical simulation of dynamic behavior and wave propagation in the medium. Two significant differences of DPCNNs with other types of neural networks are that: (1) there is a medium to which the neurons are attached where the medium can contribute to the learning, (2) the input layer is not made of nodes but it is an edge terminal which is capable of receiving a continuous function over the input edge, though it is discretized in the finite element model. A DPCNN is reduced to a perceptron if the medium is removed and the neurons are connected to each other only by wires. Continuity of the input lets the discretization of data take place intrinsically within the DPCNN instead of being applied by the user. © 2015 Elsevier Ltd
  6. Keywords:
  7. Finite element ; Neural networks ; Numerical modeling ; Wave propagation ; Algorithms ; Learning algorithms ; Neural networks ; Neurons ; Neurophysiology ; Numerical models ; Connection weights ; Continuous functions ; Continuous neural networks ; Discretization of datum ; Dynamic behaviors ; Dynamic neural networks ; Nonlinear time-dependent problems ; Propagation mechanism ; Finite element method ; Article ; Artificial neural network ; Cell adhesion ; Cell count ; Intermethod comparison ; Learning algorithm ; Mathematical analysis ; Mathematical model ; Nerve cell network ; Nerve cell plasticity ; Neurophysiology ; Nonlinear system ; Perceptron ; Priority journal ; Process model ; Sensitivity analysis
  8. Source: Neural Networks ; Volume 75 , 2016 , Pages 77-83 ; 08936080 (ISSN)
  9. URL: http://www.sciencedirect.com/science/article/pii/S0893608015002567