Modelling of Computer Communication Networks via Probabilistic Automata

Niznik, C.A.

doi:10.1108/eb005548

Cited by 5 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…neural level structures, where learning and memory have occurred. The biochemical and mathematical formalism, which is proposed and initially developed here, will realize statistical and classical entropy theory to provide a parameter which determines the following adaptive network architecture parameters: (1) graded potential and action potential intervals and the correlated informational state [15,18]; (2) neuron (computer node) input (dendrite) and output (axon) [11,12,15,18] channel probability transition matrix entries [12,14]; (3) accuracy of Probabilistic Automata representation of neurons and channels [10,14,23]; (4) number of possible routing paths for neural information [10,13,14].…”

Section: A Entropy Theorymentioning

confidence: 99%

“…These delay entries are computed from the basic computer networking Quantization Theory equation in Niznik [11,12,13,141. The individual delay component values are generated from a Probabilistic Automata Model of the computer node equated to the neural soma, the channel equated to the input dendrite links or the output axon links, and the synaptic region equated to a small computer node.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Computer networking topological and parametric representations for functional neural networks

Niznik¹,

Hoss²,

Watts³

1990

1990 IJCNN International Joint Conference on Neural Networks

View full text Add to dashboard Cite

The correlated biochemical and electrical engineering based development of the entropy theory was formalized for the parameterization of path information,i.e. storage measures. Similarly, the computer and neural network path delays were developed. Both path parameters were illustrated for the computer networking topological representation of two neural function organs and their interconnection, i.e., the star, the Hippocampus computer network representation, and the wheel with a hub, the Cerebellum computer network representation. The information measures illustrated the topologically motivated data compression and connectivity differences. The following computer networking issues are realized in the topological neural network conversion to a functional computer network derivation of path delay and storage parameters; load, real time requests for various topological structures, concurrency in centralized and distributed networks, deadlock and livelock control, and contention resolution. Category theory is utilized as the mathematical formulation for the definition of simulation in this software theory. I . MATHEMATICAL FRAMEWORK FOR COMPUTER NETWORKING/NEURALDuring the past ten years, neural networking, which exhibits characteristics linked to the operation of the human brain intelligence states, has surfaced as a research area developing parallel to computer networking. The interaction between disciplines of electrical engineering, physics and biochemistry with the interdisciplinary idea of neural prosthetic hardware and software replacement components, and its connection to computer networking, was suggested by Niznik [14], Niznik and Newcomb [16,17] and Niznik, Hoss, and Watts [15,18]. The distinct interaction theory concept represents the transfer of theoretical and heuristic concepts between the disciplines of electrical engineering, computer networking and neural networking to extend their definition of network operation and control. Category theory is the basic structure realized for the interaction of the mathematical techniques of iterative software systems. The overall illustration of this statement occurs in the characteristic terminology and parameters which comprise the category. Simulation in the context of a category is defined as "a mapping where Machine B simulates the activity of Machine A if one step in Machine B and the halting of Machine A forces Machine B to halt" [19]. Simulation is the methodology for programmatically specifying and evaluating the performance of processes in computer networks and functions that the neural networks comprise. Therefore, category theory formalizes the finite identification of an infinite number of network paths, whose analogy is the infinite number of sentences, and the finite number of rules to create the sentences in a simulation language. TOPOLOGICAL FORMALISMSIn [18] Niznik, Hoss and Watts have implemented the theoretical basis for the development of the Robotic Quantization Controlled Sensory[RQCS] System, a section of the robotic neural network. In this...

show abstract