Generating context-free languages using spiking neural P systems with structural plasticity

Cruz, Ren Tristan A. de la; Cabarle, Francis George C.; Adorna, Henry N.

doi:10.1007/s41965-019-00021-2

Cited by 32 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ref. [10] proposed an SN P system SNPSPS for synaptic remodeling accomplished by the invocation of rules in neurons. Ref.…”

Section: Introductionmentioning

confidence: 99%

Performing Arithmetic Operations with Locally Homogeneous Spiking Neural P Systems

Zhang¹,

Hu²,

Li³

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

The parallelism of rule execution in membrane computing provides support for improving computational efficiency. Membrane computing models have been applied in many fields. In arithmetic operations, designing basic arithmetic operation spiking neural P systems using fewer neurons and rule types has been an important field of membrane computing application research in recent years. We discuss the application of locally homogeneous spiking neural P systems in arithmetic operations. The purpose is to design a spiking neural P system with fewer neurons and rule types to perform arithmetic operations. We designed the addition and subtraction of a locally homogeneous spiking neural P system without weight and delay. They include two input neurons to achieve any two binary number subtraction, one input neuron to achieve any two binary number addition and subtraction, and one input neuron to achieve any n binary number addition and subtraction. This is an attempt to apply the locally homogeneous spiking neural P system in arithmetic operations. Compared with the current excellent spiking neural P system performing arithmetic operations, our designed locally homogeneous spiking neural P system is more concise. The system we designed reduces the number of neurons required for n number addition operations by k − 6 and reduces the number of rule types by 5k − 14.

show abstract

“…Ref. [10] proposed an SN P system SNPSPS for synaptic remodeling accomplished by the invocation of rules in neurons. Ref.…”

Section: Introductionmentioning

confidence: 99%

Performing Arithmetic Operations with Locally Homogeneous Spiking Neural P Systems

Zhang¹,

Hu²,

Li³

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…These variants have solved many theory and applications problems. [28][29][30] As well, SN P systems have been successfully applied in various real-world scenarios, including combinatorial optimisation, 31,32 fault diagnosis 33 and arithmetic calculator. 34 The capabilities of SN P systems for addressing classification problems have also been investigated (see e.g.…”

Section: Introductionmentioning

confidence: 99%

A Layered Spiking Neural System for Classification Problems

Zhang

Rong

et al. 2022

Int. J. Neur. Syst.

View full text Add to dashboard Cite

Biological brains have a natural capacity for resolving certain classification tasks. Studies on biologically plausible spiking neurons, architectures and mechanisms of artificial neural systems that closely match biological observations while giving high classification performance are gaining momentum. Spiking neural P systems (SN P systems) are a class of membrane computing models and third-generation neural networks that are based on the behavior of biological neural cells and have been used in various engineering applications. Furthermore, SN P systems are characterized by a highly flexible structure that enables the design of a machine learning algorithm by mimicking the structure and behavior of biological cells without the over-simplification present in neural networks. Based on this aspect, this paper proposes a novel type of SN P system, namely, layered SN P system (LSN P system), to solve classification problems by supervised learning. The proposed LSN P system consists of a multi-layer network containing multiple weighted fuzzy SN P systems with adaptive weight adjustment rules. The proposed system employs specific ascending dimension techniques and a selection method of output neurons for classification problems. The experimental results obtained using benchmark datasets from the UCI machine learning repository and MNIST dataset demonstrated the feasibility and effectiveness of the proposed LSN P system. More importantly, the proposed LSN P system presents the first SN P system that demonstrates sufficient performance for use in addressing real-world classification problems.

show abstract

“…There are also works that focus on simulating SN P systems, as they are parallel in nature, in GPUs such as [9,10] and more recently in [11][12][13]. Much theoretical work has been done on SN P systems, e.g., their normal forms [14][15][16], formal representations [17][18][19], and their relations to classical models of computation [20][21][22][23][24][25] with a short and recent survey in [26]. After much theoretical work, more recently the work to apply SN P systems to real-world problems becomes even more active, with some early works on image processing e.g., [27] and more recently in [28], use for cryptography [29][30][31], use of evolutionary algorithms to design SN P systems [32][33][34], in pattern recognition [35,36], computational biology [37], with a recent survey in [38].…”

Section: Introductionmentioning

confidence: 99%

Snapse: A Visual Tool for Spiking Neural P Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Spiking neural P (SN P) systems are models of computation inspired by spiking neurons and part of the third generation of neuron models. SN P systems are equivalent to Turing machines and are able to solve computationally hard problems using a space-time trade-off. Research in SN P systems theory is especially active, more so in recent years as more efforts are directed towards their real-world applications. Usually, SN P systems are represented visually as a directed graph and simulated through mainly text-based simulations or tables. Thus, there is a need for tools that can simulate and create SN P Systems in a visual and easy-to-use manner. Snapse is such a tool which aims to hasten the speed and ease at which researchers may create and experiment with SN P systems. Furthermore, visual tools such as Snapse can help further bring SN P systems outside of theoretical computer science.

show abstract

Generating context-free languages using spiking neural P systems with structural plasticity

Cited by 32 publications

References 25 publications

Performing Arithmetic Operations with Locally Homogeneous Spiking Neural P Systems

Performing Arithmetic Operations with Locally Homogeneous Spiking Neural P Systems

A Layered Spiking Neural System for Classification Problems

Snapse: A Visual Tool for Spiking Neural P Systems

Contact Info

Product

Resources

About