Search

Spiking neural P systems (SN P systems) are a class of distributed and parallel neural-like computing models, inspired from the way neurons communicate by means of spikes. In this paper, a new variant of the systems, called SN P systems with learning functions, is introduced. Such systems can dynamically strengthen and weaken connections among neurons during the computation. A class of specific SN P systems with simple Hebbian learning function is constructed to recognize English letters. The experimental results show that the SN P systems achieve average accuracy rate 98.76% in the test case without noise. In the test cases with low, medium, and high noises, the SN P systems outperform back propagation neural networks and probabilistic neural networks. Moreover, comparing with spiking neural networks, SN P systems perform a little better in recognizing letters with noise. The result of this paper is promising in terms of the fact that it is the first attempt to use SN P systems in pattern recognition after many theoretical advancements of SN P systems, and SN P systems exhibit the feasibility for tackling pattern recognition problems.

Community detection is an important tool to analyze hidden information such as functional module and topology structure in complex networks. Compared with traditional community detection, it is more challenging to find overlapping communities in complex networks, especially when the networks are of large scales. Among various overlapping community detection techniques, the well-known clique percolation method (CPM) has shown promising performance in terms of quality of found communities, but suffers from serious curse of dimensionality due to its high computational complexity, which makes it very unlikely to be applied to large-scale networks. To address this issue, in this paper, we propose a weak-CPM for overlapping community detection in large-scale networks. A new measure for characterizing the similarity between weak cliques is also suggested to check whether the weak cliques can be merged into a community. Experimental results on synthetic and real-world networks demonstrate the competitive performance of the proposed method over six popular overlapping community detection algorithms in terms of both computational efficiency and quality of found communities. In addition, the proposed method is also suitable for detecting large-scale networks with an unclear community structure under different levels of overlapping density and overlapping diversity, which is an important property of many real-world complex networks.

Cell-like spiking neural P systems are a variant of standard spiking neural P systems, which have a cell-like instead of neural-like architecture. It has been proved that cell-like spiking neural P systems can generate Turing computable sets of numbers. In this work, the computational power of cell-like spiking neural P systems as language generators is investigated. Characterization of finite languages is obtained with cell-like spiking neural P systems when the number of spikes produced is less than the number of spikes consumed, and characterization of recursively enumerable languages is obtained by cell-like spiking neural P systems when there is no restriction on the number of produced spikes. The relationships of the languages generated by cell-like spiking neural P systems with regular, non-context-free and non-semilinear languages are also investigated.

Spiking neural P systems with rules on synapses are a new variant of spiking neural P systems. In the systems, the neuron contains only spikes, while the spiking/forgetting rules are moved on the synapses. It was obtained that such system with 30 neurons (using extended spiking rules) or with 39 neurons (using standard spiking rules) is Turing universal. In this work, this number is improved to 6. Specifically, we construct a Turing universal spiking neural P system with rules on synapses having 6 neurons, which can generate any set of Turing computable natural numbers. As well, it is obtained that spiking neural P system with rules on synapses having less than two neurons are not Turing universal: i) such systems having one neuron can characterize the family of finite sets of natural numbers; ii) the family of sets of numbers generated by the systems having two neurons is included in the family of semi-linear sets of natural numbers.

Axon P systems are computing models with a linear structure in the sense that all nodes (i.e., computing units) are arranged one by one along the axon. Such models have a good biological motivation: an axon in a nervous system is a complex information processor of impulse signals. Because the structure of axon P systems is linear, the computational power of such systems has been proved to be greatly restricted; in particular, axon P systems are not universal as language generators. It remains open whether axon P systems are universal as number generators. In this paper, we prove that axon P systems are universal as both number generators and function computing devices, and investigate the number of nodes needed to construct a universal axon P system. It is proved that four nodes (respectively, nine nodes) are enough for axon P systems to achieve universality as number generators (respectively, function computing devices). These results illustrate that the simple linear structure is enough for axon P systems to achieve a desired computational power.

Surrogate-assisted evolutionary algorithms have been developed mainly for solving expensive optimization problems where only a small number of real fitness evaluations are allowed. Most existing surrogate-assisted evolutionary algorithms are designed for solving low-dimensional single or multiobjective optimization problems, which are not well suited for many-objective optimization. This paper proposes a surrogateassisted many-objective evolutionary algorithm that uses an artificial neural network to predict the dominance relationship between candidate solutions and reference solutions instead of approximating the objective values separately. The uncertainty information in prediction is taken into account together with the dominance relationship to select promising solutions to be evaluated using the real objective functions. Our simulation results demonstrate that the proposed algorithm outperforms the state-of-the-art evolutionary algorithms on a set of manyobjective optimization test problems.

Recently, Gutiérrez-Naranjo and Leporati considered performing basic arithmetic operations on a new class of bio-inspired computing devices-spiking neural P systems (for short, SN P systems). However, the binary encoding mechanism used in their research looks like the encoding approach in electronic circuits, instead of the style of spiking neurons (in usual SN P systems, information is encoded as the time interval between spikes). In this work, four SN P systems are constructed as adder, subtracter, multiplier, and divider, respectively. In these systems, a number is inputted to the system as the interval of time elapsed between two spikes received by input neuron, the result of a computation is the time between the moments when the output neuron spikes.