Inspired by Eckhorn’s neuron model that emulates a mammal’s visual cortex, this paper proposes a new kind of neural-like P system, called a coupled neural P (CNP) system. The CNP system consists of some coupled neurons, each with three components: receptive field, modulation, and output module. CNP systems are a kind of distributed parallel-computing model with a directed graph structure like spiking neural P systems. Moreover, CNP systems have a nonlinear coupled-modulation characteristic and a dynamic threshold mechanism. The computational power of CNP systems is discussed. Specifically, it is proved that CNP systems as number-generating devices are Turing universal. Moreover, we provide a small universal CNP system for function-computing devices.

Coupled Neural P Systems

Motivated by the mechanism of inhibitory synapses, a new kind of spiking neural P (SNP) system rules, called inhibitory rules, is introduced in this paper. Based on this, a new variant of SNP systems is proposed, called spiking neural P systems with inhibitory rules (SNP-IR systems). Different from the usual firing rules in SNP systems, the firing condition of an inhibitory rule not only depends on the state of the neuron associated with the rule but also is related to the states of other neurons. Moreover, from the perspective of topological structure, the new variant is shown as a directed graph with inhibitory arcs, and therefore seems to have more powerful control. The computational completeness of SNP-IR systems is discussed. In particular, it is proved that SNP-IR systems are Turing universal number accepting/generating devices. Moreover, we obtain a small universal function-computing device for SNP-IR systems consisting of 100 neurons.

/pdf/spiking-neural-p-systems-with-inhibitory-rules-305uqj8whg.pdf

Spiking neural P systems with inhibitory rules

The authors present a cognitively inspired mathematical learning framework called Neural Modeling Fields (NMF). They apply it to learning and recognition of situations composed of objects. NMF successfully overcomes the combinatorial complexity of associating subsets of objects with situations and demonstrates fast and reliable convergence. The implications of the current results for building multi-layered intelligent systems are also discussed.

https://leonid-perlovsky.com/new-materials/11,%20IJNCR_Situations.pdf

Cognitively Inspired Neural Network for Recognition of Situations

Dendrite P systems.

This paper proposes a new variant of spiking neural P systems (in short, SNP systems), nonlinear spiking neural P systems (in short, NSNP systems). In NSNP systems, the state of each neuron is deno...

Nonlinear Spiking Neural P Systems.

We study two very simple variants of P colonies: systems with only one object inside the cells, and systems with insertion-deletion programs, so called P colonies with senders and consumers. We show that both of these extremely simple types of systems are able to compute any recursively enumerable set of vectors of

http://univagora.ro/jour/index.php/ijccc/article/download/2430/896

Variants of P Colonies with Very Simple Cell Structure

We continue the investigation of P colonies introduced in [8], a class of abstract computing devices composed of independent membrane agents, acting and evolving in a shared environment.

We decrease the number of agents sufficient to guarantee computational completeness of P colonies with one and with two objects inside each agent, respectively, owing some special restrictions to the type of programs. We characterize the generative power of the partially blind machine by the generative power of special P colonies.

/pdf/on-the-number-of-agents-in-p-colonies-1tuu17zgks.pdf

On the number of agents in P colonies

P colonies: Survey

We study P colonies introduced in (8) as a class of abstract computing devices composed of independent membrane agents, acting and evolving in a shared environment. In the present paper especially P colonies are considered, which are homogeneous with respect to the type of rules in each program of agents. The number of agents, as well as the number of programs in each agent are bounded, which are sufficient to guarantee computational completeness of homoge- neous P colonies. We present results for P colonies with one and with two objects inside each agent.

Homogeneous p colonies

1 Institute of Computer Science, Silesian University in Opava Bezrucovo nam. 13, 74601 Opava, Czech Republic {ludek.cienciala,lucie.ciencialova}@fpf.slu.cz 2 Computer and Automation Research Institute Hungarian Academy of Sciences Kende utca 13-17, 1111 Budapest, Hungary {csuhaj,vaszil}@sztaki.hu 3 Department of Algorithms and Their Applications Faculty of Informatics, Eotvos Lorand University Pazmany Peter setany 1/c, 1117 Budapest, Hungary

/pdf/pcol-automata-recognizing-strings-with-p-colonies-3nhk828mv4.pdf

Lucie Ciencialová

Papers

Variants of P Colonies with Very Simple Cell Structure

On the number of agents in P colonies

P colonies: Survey

Homogeneous p colonies

PCoL automata: recognizing strings with P colonies