In the last few decades, Artificial Neural Networks have become more and more important, evolving into a powerful tool to implement learning algorithms. Spiking neural networks represent the third generation of Artificial Neural Networks; they have earned growing significance due to their remarkable achievements in pattern recognition, finding extensive utility across diverse domains such as e.g. diagnostic medicine. Usually, Spiking Neural Networks are slightly less accurate than other Artificial Neural Networks, but they require a reduced amount of energy to perform calculations; this amount of energy further reduces in a very significant manner if they are implemented on hardware specifically designed for them, like neuromorphic hardware. In this work, we focus on exploring the versatility of Spiking Neural Networks and their potential applications across a range of scenarios by exploiting their adaptability and dynamic processing capabilities, which make them suitable for various tasks. A first rough network is designed based on the dataset's general attributes; the network is then refined through an extensive grid search algorithm to identify the optimal values for hyperparameters. This dual-step process ensures that the Spiking Neural Network can be tailored to diverse and potentially very different situations in a direct and intuitive manner. We test this by considering three different scenarios: epileptic seizure detection, both considering binary and multi-classification tasks, as well as wine classification. The proposed methodology turned out to be highly effective in binary class scenarios: the Spiking Neural Networks models achieved significantly lower energy consumption compared to Artificial Neural Networks while approaching nearly 100% accuracy. In the case of multi-class classification, the model achieved an accuracy of approximately 90%, thus indicating that it can still be further improved.

Spiking Neural P Systems are parallel and distributed computational models inspired by biological neurons, emerging from membrane computing and applied to solving computationally difficult problems. This paper focuses on the computational complexity of such systems using neuron division rules and colored spikes for the SAT problem. We prove a conjecture stated in a recent paper, showing that enhancing the model with an input module reduces computing time. Additionally, we prove that the inclusion of budding rules extends the model’s capability to solve all problems in the complexity class PSPACE. These findings advance research on Spiking Neural P Systems and their application to complex problems; however, whether both budding rules and division rules are required to extend these methods to problem domains beyond the NP class remains an open question.

Spiking Neural Networks (SNNs) are powerful and biologically plausible models of neural processing and represent a transition to a new generation of neural networks, as they address the problem of high resource requirements by significantly reducing energy consumption. In this paper we investigate the use of SNNs for the diagnosis of COVID-19 cases from chest x-rays, by proposing a simple Spiking Neural Network (SNN) that proves to be effective despite the low resources requested with respect to other solutions proposed in the literature. The paper explains the architecture of the SNN and evaluates the performance of the model in terms of both result accuracy and energy consumption. Experimental results show competitive performance in terms of accuracy and a significant reduction in energy consumption.

A variant of membrane computing models called Spiking Neural P systems (SNP systems) closely mimics the structure and behavior of biological neurons. As third-generation neural networks, SNP systems have flexible architectures allowing the design of bio-inspired machine learning algorithms. This paper proposes Modular Spiking Neural P (MSNP) systems to solve image classification problems, a novel SNP system to be applied in scenarios where hundreds or even thousands of different classes are considered. A main issue to face in such situations is related to the structural complexity of the network. MSNP systems devised in this work allow to approach the general classification problem by dividing it in smaller parts, that are then faced by single entities of the network. As a benchmark dataset, the Oxford Flowers 102 dataset is considered, consisting of more than 8000 pictures of flowers belonging to the 102 species commonly found in the UK. These classes sometimes present large variations within them, may be also very similar to one another, and different images of the same subject may differ a lot. The work describes the architecture of the MSNP system, based on modules focusing on a specific class, their training phase, and the evaluation of the model both concerning result accuracy as well as energy consumption. Experimental results on image classification problems show that the model achieves good results, but is strongly connected to image quality, mainly depending on the frequency of images, remarkable changes of pose, images not centered, and subject mostly not shown.

Tissue P systems with evolutional symport/antiport rules are a variant of tissue P systems, where objects are communicated through regions by symport/antiport rules, and objects may evolve during this process. It is known that such systems are able to solve NP problems in a polynomial time (and exponential space), when cell division is allowed. In this work, we continue to investigate the computational complexity aspects for tissue P systems with evolutional symport/antiport rules. We prove that problems beyond NP can also be solved. In particular, we show that deterministic systems of this type are able to solve all problems in the complexity class PP. Moreover, if non-deterministic systems are considered, then all problems in the class PSPACE can be solved.

Spiking neural membrane systems are models of computation inspired by the natural functioning of the brain using the concepts of neurons and synapses, and represent a way of building computational systems of a biological inspiration. A variant of such a model, allowing to create new neurons and synapses during the computation, has been considered in the literature to attack computationally hard problems, like problems in the class NP. In this work, we investigate the computational properties of this variant, by proposing three solutions to computationally hard problems, by models with different features, and comparing them with those present in the literature. In particular, we first propose a nondeterministic solution for the NP-complete problem 3-SAT, by a model using dynamic organization of synapses. Then, we propose a deterministic solution for the same problem, by a model using neuron division and dissolution rules. Finally, we show that dissolution rules are not strictly necessary (by accepting a certain amount of slowdown in computing time), and that also problems beyond the class NP can be solved by systems with neuron division alone.

Abstract Spiking neural P systems are parallel and distributed computation devices which are inspired by the neuro-physiological behavior of biological neurons. In this paper we will present, with a tutorial approach, the main underlying ideas and the most interesting variants that have been proposed in the literature. In particular, we will discuss the results on the computational power of these models, both in terms of Turing completeness and of efficiency in solving hard problems, under different assumptions for information encoding, form and application of rules, and bounds on the main parameters defining the systems.

This special issue is dedicated to Giancarlo Mauri on the occasion of his 70th birthday.Giancarlo is a well-known prolific

Traditionally, P systems allow their membranes or cells to grow exponentially (or even more) in volume with respect to the size of the multiset of objects they contain in the initial configuration. This behaviour is, in general, biologically unrealistic, since large cells tend to divide in order to maintain a suitably large surface-area-to-volume ratio. On the other hand, it is usually the number of cells that needs to grow exponentially with time by binary division in order to solve NP-complete problems in polynomial time. In this paper we investigate families of tissue P systems with cell division where each cell has a small volume (i.e., sub-polynomial with respect to the input size), assuming that each bit of information contained in the cell, including both those needed to represent the multiset of objects and the cell label, occupies a unit of volume. We show that even a constant volume bound allows us to reach computational universality for families of tissue P systems with cell division, if we employ an exponential-time uniformity condition on the families. Furthermore, we also show that a sub-polynomial volume does not suffice to solve NP-complete problems in polynomial time, unless the satisfiability problem for Boolean formulae can be solved in sub-exponential time, and that solving an NP-complete problem in polynomial time with logarithmic cell volume implies P = NP.

Polynomial-time P systems with active membranes characterise PSPACE by exploiting membranes nested to a polynomial depth, which may be subject to membrane division rules. When only elementary (leaf) membrane division rules are allowed, the computing power decreases to P PP = P #P , the class of problems solvable in polynomial time by deterministic Turing machines equipped with oracles for counting (or majority) problems. In this paper we investigate a variant of intermediate power, limiting membrane nesting (hence membrane division) to constant depth, and we prove that the resulting P systems can solve all problems in the counting hierarchy CH, which is located between P PP and PSPACE. In particular, for each integer k ≥ 0 we provide a lower bound to the computing power of P systems of depth k.

Membrane systems, also called P systems, are an interesting class of parallel and distributed models of computation inspired by cell biology. They have been thoroughly investigated in the literature, both from the theoretical standpoint—analysing their computing power and efficiency—and as tools to model natural phenomena. In this article, we focus on the complexity theory of P systems with active membranes, a variant of P systems where the membranes themselves affect the applicability of rules and change (both in number and structurally) during computations. We summarize the main results on their space complexity, and describe some recent improvements related to time complexity, proved via a few general proof techniques.

We show that a constant amount of space is sufficient to simulate a polynomial-space bounded Turing machine by P systems with active membranes. We thus obtain a new characterisation of PSPACE, which raises interesting questions about the definition o

We consider the structure of the intestinal epithelial tissue and of cell–cell junctions as the biological model inspiring a new class of P systems. First we define the concept of cell polarity, a formal property derived from epithelial cells, which present morphologically and functionally distinct regions of the plasma membrane. Then we show two preliminary results for this new model of computation: on the theoretical side, we show that P systems with cell polarity are computationally (Turing) complete; on the modelling side, we show that the transepithelial movement of glucose from the intestinal lumen into the blood can be described by such a formal system. Finally, we define tissue P systems with cell polarity, where each cell has fixed connections to the neighbouring cells and to the environment, according to both the cell polarity and specific cell–cell junctions.