Random Neural Networks with Negative and Positive Signals and Product Form Solution

@article{Gelenbe1989RandomNN,
  title={Random Neural Networks with Negative and Positive Signals and Product Form Solution},
  author={Erol Gelenbe},
  journal={Neural Computation},
  year={1989},
  volume={1},
  pages={502-510}
}
  • E. Gelenbe
  • Published 1989
  • Mathematics, Computer Science
  • Neural Computation
We introduce a new class of random neural networks in which signals are either negative or positive. A positive signal arriving at a neuron increases its total signal count or potential by one; a negative signal reduces it by one if the potential is positive, and has no effect if it is zero. When its potential is positive, a neuron fires, sending positive or negative signals at random intervals to neurons or to the outside. Positive signals represent excitatory signals and negative signals… Expand
G-Nets and Learning Recurrent Random Networks
TLDR
A new recurrent random neural network in which “negative” and “positive” signals circulate, modelling inhibitory and excitatory signals of a neural network using gradient descent is described. Expand
Stability of the Random Neural Network Model
  • E. Gelenbe
  • Mathematics, Computer Science
  • Neural Computation
  • 1990
TLDR
It is shown that whenever the solution to the signal flow equations of the Random Network exists, it is unique and therefore that the network has a well-defined steady-state behavior. Expand
Stability of the Random Neural Network Model
TLDR
It is shown that in the Markovian case, this model has product form, i.e. the steady-state probability distribution of its potential vector is the product of the marginal probabilities of the potential at each neuron. Expand
Random Neural Networks with Multiple Classes of Signals1)
TLDR
The multiple signal class random model with exponential firing times, Poisson external signal arrivals, and Markovian signal movements between neurons, has product form and can be computed simply from the solution of a system of simultaneous non-linear equations. Expand
Random Neural Networks with Multiple Classes of Signals
TLDR
Here it is shown that the multiple signal class random model with exponential interfiring times, Poisson external signal arrivals, and Markovian signal movements between neurons has product form; this implies that the distribution of its state can be computed simply from the solution of a system of simultaneous nonlinear equations. Expand
G-networks: a unifying model for neural and queueing networks
  • E. Gelenbe
  • Computer Science, Mathematics
  • MASCOTS
  • 1993
TLDR
The results concerning a new stochastic network, which was initially motivated by neural network modelling, are surveyed, and extensions of the model to the case of “multiple signal classes”, and to “networks with triggered customer motion” are presented. Expand
Image processing with the random neural network (RNN)
We discuss novel approaches for image enlargement and fusion using the RNN, after successful results with still and video compression and image segmentation. In the RNN model signals in the form ofExpand
The Random Neural Network: A Survey
TLDR
A review of the theory, extension models, learning algorithms and applications of the RNN, which has been applied in a variety of areas including pattern recognition, classification, image processing, combinatorial optimization and communication systems. Expand
An Investigation of the Analogy betweenthe Random Network and the Hop eldNetworkAristidis
In recent publications, a new neural network model, called the random network, has been introduced, in which excitation and inhibition are represented by positive and negative signals. It has beenExpand
FAST NON-NEGATIVE LEAST-SQUARES LEARNING IN THE RANDOM NEURAL NETWORK
  • S. Timotheou
  • Computer Science
  • Probability in the Engineering and Informational Sciences
  • 2016
TLDR
Simulation results in the context of optimizing the performance of a disaster management problem using supervised learning verify the efficiency of the approach, achieving two orders of magnitude execution speedup and improved solution quality compared to state-of-the-art algorithms. Expand
...
1
2
3
4
5
...

References

SHOWING 1-5 OF 5 REFERENCES
Stability of the Random Neural Network Model
  • E. Gelenbe
  • Mathematics, Computer Science
  • Neural Computation
  • 1990
TLDR
It is shown that whenever the solution to the signal flow equations of the Random Network exists, it is unique and therefore that the network has a well-defined steady-state behavior. Expand
Analysis and Synthesis of Computer Systems
TLDR
This paper presents a monographs on characterisation and control of Achievable Performance Control of Performance in Mutliple-Resource Systems and a Queue with Server of Walking Type. Expand
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
The fundamental principles, basic mechanisms, and formal analyses involved in the development of parallel distributed processing (PDP) systems are presented in individual chapters contributed byExpand
Principles of Neural Science
TLDR
The editors have done a masterful job of weaving together the biologic, the behavioral, and the clinical sciences into a single tapestry in which everyone from the molecular biologist to the practicing psychiatrist can find and appreciate his or her own research. Expand
Introduction to Networks of Queues
  • Wiley, New
  • 1986