Spiking Neural P Systems Research Articles

CLSTM-SNP: Convolutional Neural Network to Enhance Spiking Neural P Systems for Named Entity Recognition Based on Long Short-Term Memory Network

AbstractMembrane computing is a type of parallel computing system (generally called P system) abstracted from information exchange mechanisms in biological cells, tissues, or neurons, which can process data in a distributed and interpretable manner. LSTM-SNP, the first model of long short-term memory networks based on parameterized nonlinear Spiking neural P systems, was proposed recently. However, a systematic understanding and leveraging of the LSTM-SNP model to address named entity recognition (NER) and other natural language processing (NLP) tasks are still lacking. The bottleneck of the NER task lies in the scarcity of data and the vague definition of entity edges. Most approaches center on dataset handling, and there have been few attempts to address the issue in Spiking neural P (SNP) systems. This paper proposes a model named CLSTM-SNP based on the LSTM-SNP, aiming to tackle the NER problem in the field of SNP systems for the first time. First, this study employs a CNN layer to obtain character-level characteristics. Second, GloVe word vectors are utilized as word representations. Third, the research employs the LSTM-SNP to analyze textual features. We subsequently studied CLSTM-SNP’s effectiveness in addressing NER problems on CoNLL-2003 and OntoNotes 5.0 datasets and compared it to the results of five other baseline methods. Our model CLSTM-SNP achieved a macro F1-score of 89.2 $$\%$$ % on CoNLL-2003 and 75.5$$\%$$ % on OntoNotes 5.0, respectively. The performance of CLSTM-SNP and LSTM-SNP indicates a great potential for handling named entity recognition or other sequential tasks in NLP.

Nonlinear Spiking Neural Systems With Autapses for Predicting Chaotic Time Series.

Spiking neural P (SNP) systems are a class of distributed and parallel neural-like computing models that are inspired by the mechanism of spiking neurons and are 3rd-generation neural networks. Chaotic time series forecasting is one of the most challenging problems for machine learning models. To address this challenge, we first propose a nonlinear version of SNP systems, called nonlinear SNP systems with autapses (NSNP-AU systems). In addition to the nonlinear consumption and generation of spikes, the NSNP-AU systems have three nonlinear gate functions, which are related to the states and outputs of the neurons. Inspired by the spiking mechanisms of NSNP-AU systems, we develop a recurrent-type prediction model for chaotic time series, called the NSNP-AU model. As a new variant of recurrent neural networks (RNNs), the NSNP-AU model is implemented in a popular deep learning framework. Four datasets of chaotic time series are investigated using the proposed NSNP-AU model, five state-of-the-art models, and 28 baseline prediction models. The experimental results demonstrate the advantage of the proposed NSNP-AU model for chaotic time series forecasting.

Gated Spiking Neural P Systems for Time Series Forecasting.

Spiking neural P (SNP) systems are a class of neural-like computing models, abstracted by the mechanism of spiking neurons. This article proposes a new variant of SNP systems, called gated spiking neural P (GSNP) systems, which are composed of gated neurons. Two gated mechanisms are introduced in the nonlinear spiking mechanism of GSNP systems, consisting of a reset gate and a consumption gate. The two gates are used to control the updating of states in neurons. Based on gated neurons, a prediction model for time series is developed, known as the GSNP model. Several benchmark univariate and multivariate time series are used to evaluate the proposed GSNP model and to compare several state-of-the-art prediction models. The comparison results demonstrate the availability and effectiveness of GSNP for time series forecasting.

LSTM-SNP: A long short-term memory model inspired from spiking neural P systems

Spiking neural P (SNP) systems are a class of neural-like membrane computing models that are abstracted by applying the mechanisms of spiking neurons. In SNP systems, each spiking neuron has three characteristics: (i) internal state, (ii) spike consumption, and (iii) spike generation. These three characteristics are used to form a parameterised nonlinear SNP system, which has a nonlinear spiking mechanism, three nonlinear gate functions, and trainable parameters. Based on the parameterised nonlinear SNP system, we develop a novel variant of long short-term memory (LSTM), called the LSTM-SNP model. LSTM-SNP is a recurrent-type model that can process sequential data. Time series forecasting problems are used to conduct a case study. Five benchmark time series are used to evaluate the proposed LSTM-SNP model and compare seven state-of-the-art prediction models and five baseline prediction models. The comparison results show the effectiveness of the proposed LSTM-SNP model for time series forecasting.

Simulation of Spiking Neural P Systems with Sparse Matrix-Vector Operations

To date, parallel simulation algorithms for spiking neural P (SNP) systems are based on a matrix representation. This way, the simulation is implemented with linear algebra operations, which can be easily parallelized on high performance computing platforms such as GPUs. Although it has been convenient for the first generation of GPU-based simulators, such as CuSNP, there are some bottlenecks to sort out. For example, the proposed matrix representations of SNP systems lead to very sparse matrices, where the majority of values are zero. It is known that sparse matrices can compromise the performance of algorithms since they involve a waste of memory and time. This problem has been extensively studied in the literature of parallel computing. In this paper, we analyze some of these ideas and apply them to represent some variants of SNP systems. We also provide a new simulation algorithm based on a novel compressed representation for sparse matrices. We also conclude which SNP system variant better suits our new compressed matrix representation.

Parallel Binary Image Cryptosystem Via Spiking Neural Networks Variants.

Due to the inefficiency of multiple binary images encryption, a parallel binary image encryption framework based on the typical variants of spiking neural networks, spiking neural P (SNP) systems is proposed in this paper. More specifically, the two basic units in the proposed image cryptosystem, the permutation unit and the diffusion unit, are designed through SNP systems with multiple channels and polarizations (SNP-MCP systems), and SNP systems with astrocyte-like control (SNP-ALC systems), respectively. Different from the serial computing of the traditional image permutation/diffusion unit, SNP-MCP-based permutation/SNP-ALC-based diffusion unit can realize parallel computing through the parallel use of rules inside the neurons. Theoretical analysis results confirm the high efficiency of the binary image proposed cryptosystem. Security analysis experiments demonstrate the security of the proposed cryptosystem.

On Applications of Spiking Neural P Systems

Over the years, spiking neural P systems (SNPS) have grown into a popular model in membrane computing because of their diverse range of applications. In this paper, we give a comprehensive summary of applications of SNPS and its variants, especially highlighting power systems fault diagnoses with fuzzy reasoning SNPS. We also study the structure and workings of these models, their comparisons along with their advantages and disadvantages. We also study the implementation of these models in hardware. Finally, we discuss some new ideas which can further expand the scope of applications of SNPS models as well as their implementations.

A Complete Arithmetic Calculator Constructed from Spiking Neural P Systems and its Application to Information Fusion.

Several variants of spiking neural P systems (SNPS) have been presented in the literature to perform arithmetic operations. However, each of these variants was designed only for one specific arithmetic operation. In this paper, a complete arithmetic calculator implemented by SNPS is proposed. An application of the proposed calculator to information fusion is also proposed. The information fusion is implemented by integrating the following three elements: (1) an addition and subtraction SNPS already reported in the literature; (2) a modified multiplication and division SNPS; (3) a novel storage SNPS, i.e. a method based on SNPS is introduced to calculate basic probability assignment of an event. This is the first attempt to apply arithmetic operation SNPS to fuse multiple information. The effectiveness of the presented general arithmetic SNPS calculator is verified by means of several examples.

An Adaptive Optimization Spiking Neural P System for Binary Problems.

Optimization Spiking Neural P System (OSNPS) is the first membrane computing model to directly derive an approximate solution of combinatorial problems with a specific reference to the 0/1 knapsack problem. OSNPS is composed of a family of parallel Spiking Neural P Systems (SNPS) that generate candidate solutions of the binary combinatorial problem and a Guider algorithm that adjusts the spiking probabilities of the neurons of the P systems. Although OSNPS is a pioneering structure in membrane computing optimization, its performance is competitive with that of modern and sophisticated metaheuristics for the knapsack problem only in low dimensional cases. In order to overcome the limitations of OSNPS, this paper proposes a novel Dynamic Guider algorithm which employs an adaptive learning and a diversity-based adaptation to control its moving operators. The resulting novel membrane computing model for optimization is here named Adaptive Optimization Spiking Neural P System (AOSNPS). Numerical result shows that the proposed approach is effective to solve the 0/1 knapsack problems and outperforms multiple various algorithms proposed in the literature to solve the same class of problems even for a large number of items (high dimensionality). Furthermore, case studies show that a AOSNPS is effective in fault sections estimation of power systems in different types of fault cases: including a single fault, multiple faults and multiple faults with incomplete and uncertain information in the IEEE 39 bus system and IEEE 118 bus system.

Dendrite P systems

It was recently found that dendrites are not just a passive channel. They can perform mixed computation of analog and digital signals, and therefore can be abstracted as information processors. Moreover, dendrites possess a feedback mechanism. Motivated by these computational and feedback characteristics, this article proposes a new variant of neural-like P systems, dendrite P (DeP) systems, where neurons simulate the computational function of dendrites and perform a firing–storing process instead of the storing–firing process in spiking neural P (SNP) systems. Moreover, the behavior of the neurons is characterized by dendrite rules that are abstracted by two characteristics of dendrites. Different from the usual firing rules in SNP systems, the firing of a dendrite rule is controlled by the states of the corresponding source neurons. Therefore, DeP systems can provide a collaborative control capability for neurons. We discuss the computational power of DeP systems. In particular, it is proven that DeP systems are Turing-universal number generating/accepting devices. Moreover, we construct a small universal DeP system consisting of 115 neurons for computing functions.

An Adaptive Spiking Neural P System for Solving Vehicle Routing Problems

The capabilities of membrane computing frameworks in solving multi-objective constrained optimization problems have invited many researchers to focus their efforts on developing new methods and computational paradigms. Getting motivated from the computational completeness of membrane computing systems (P systems), this paper proposes a new way of solving vehicle routing problems (VRP) using one of the most eminent membrane computing frameworks called spiking neural P systems (SNPS). A new model for SNPS has been recommended both for finding the optimal solutions and for optimizing the parameters that are used in the calculation of minimum feasible insertion cost of the customer insertion phase of VRP without using any heuristic operators. The SNPS suggested here is an adaptive SNPS in which some potentials (ATSNPS) with learning and training facilities are incorporated. Being an NP-hard problem with numerous applications in many areas such as gas distribution management, postal delivery, and truck dispatching, the benefits of this study are far-reaching. Here, a variant of VRP called VRP with time windows (VRPTW) has been used in the proposed system. Since this is the first attempt to find solutions of VRP using ATSNPS, a comparison has been made with the algorithms used over VRPTW. The analysis of results proved that the proposed ATSNPS is substantially superior to the state-of-the-art algorithms in terms of computational time and optimizing the attributes such as the average number of vehicles used and the total distance traveled.

Spiking neural P systems with inhibitory rules

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.

Spiking neural P systems with structural plasticity

Spiking neural P (SNP) systems are a class of parallel, distributed, and nondeterministic computing models inspired by the spiking of biological neurons. In this work, the biological feature known as structural plasticity is introduced in the framework of SNP systems. Structural plasticity refers to synapse creation and deletion, thus changing the synapse graph. The programming therefore of a brain-like model, the SNP system with structural plasticity (SNPSP system), is based on how neurons connect to each other. SNPSP systems are also a partial answer to an open question on SNP systems with dynamism only for synapses. For both the accepting and generative modes, we prove that SNPSP systems are universal. Modifying SNPSP systems semantics, we introduce the spike saving mode and prove that universality is maintained. In saving mode, however, a deadlock state can arise, and we prove that reaching such a state is undecidable. Lastly, we provide one technique in order to use structural plasticity to solve a hard problem: a constant time, nondeterministic, and semi-uniform solution to the NP-complete problem Subset Sum.

An optimization spiking neural p system for approximately solving combinatorial optimization problems.

Membrane systems (also called P systems) refer to the computing models abstracted from the structure and the functioning of the living cell as well as from the cooperation of cells in tissues, organs, and other populations of cells. Spiking neural P systems (SNPS) are a class of distributed and parallel computing models that incorporate the idea of spiking neurons into P systems. To attain the solution of optimization problems, P systems are used to properly organize evolutionary operators of heuristic approaches, which are named as membrane-inspired evolutionary algorithms (MIEAs). This paper proposes a novel way to design a P system for directly obtaining the approximate solutions of combinatorial optimization problems without the aid of evolutionary operators like in the case of MIEAs. To this aim, an extended spiking neural P system (ESNPS) has been proposed by introducing the probabilistic selection of evolution rules and multi-neurons output and a family of ESNPS, called optimization spiking neural P system (OSNPS), are further designed through introducing a guider to adaptively adjust rule probabilities to approximately solve combinatorial optimization problems. Extensive experiments on knapsack problems have been reported to experimentally prove the viability and effectiveness of the proposed neural system.

An Overview of Membrane Computing

School of Computer and Information, Anqing Normal University, Anqing 246133, Anhui, ChinaMembrane computing is a new branch of natural computing whose aim is to abstract computingideas from the structure and the functioning of living cells, as well as from the cell cooperationin tissues, populations of cells and the brain. The obtained models are called P systems. Theresearch in this area developed very fast, both towards theory, such as Turing computability, lan-guage and automata theory (e.g., characterizations of Turing completeness), computational effi-ciency (polynomial solutions to NP-complete problems by trading off time to space) and applications(in system biology, bio-medicine, computer graphics, approximate optimization, robot control, cryp-tography, ecology and economics modeling, etc.). There are three main classes of P systems: (1)cell-like P systems inspired from living cells, (2) tissue-like P systems inspired from tissues, and(3) neural-like P systems inspired from neural systems. In this paper, we briefly introduce cell-likeand tissue-like P systems, and then discuss a class of neural-like P systems, called spiking neuralP systems, in details: the formal definition of the system is firstly introduced, and some results ofthe systems are recalled in two aspects: computational completeness and computational efficiency.

Sequential SNP systems based on min/max spike number

We consider the properties of spiking neural P (SNP) systems that work in a sequential manner. These SNP systems are a class of computing devices recently introduced as a bridge between spiking neural nets and membrane computing. The general sequentiality of these systems was considered previously; now we focus on the sequentiality induced by the spike number: at each step, the neuron with the maximum (or minimum) number of spikes among the neurons that are active (can spike) will fire. This strategy corresponds to a global view of the whole network that makes the system sequential. We study the properties of this type of a restriction (i.e. considering the case of sequentiality induced by the function maximum defined on numbers of spikes as well as the case of the sequentiality induced by the function minimum similarly defined on numbers of spikes). Several universality results are obtained for the cases of maximum and minimum induced sequentiality.