Henry N. Adorna

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.

A spiking neural p system simulator based on CUDA

In this paper we present a Spiking Neural P system (SNP system) simulator based on graphics processing units (GPUs). In particular we implement the simulator using NVIDIA CUDA enabled GPUs. The massively parallel architecture of current GPUs is very suitable for the maximally parallel computations of SNP systems. We simulate a wider variety of SNP systems, after presenting a previous work on SNP system matrix representation which led to their simulation in GPUs, and the simulation algorithm included here. Finally, we compare and present the performance speedups of the CPU-GPU based simulator over the CPU only simulator.

Matrix representation of spiking neural P systems

Spiking neural P systems (SN P systems, for short) are a class of distributed parallel computing devices inspired from the way neurons communicate by means of spikes. In this work, a discrete structure representation of SN P systems with extended rules and without delay is proposed. Specifically, matrices are used to represent SN P systems. In order to represent the computations of SN P systems by matrices, configuration vectors are defined to monitor the number of spikes in each neuron at any given configuration; transition net gain vectors are also introduced to quantify the total amount of spikes consumed and produced after the chosen rules are applied. Nondeterminism of the systems is assured by a set of spiking transition vectors that could be used at any given time during the computation. With such matrix representation, it is quite convenient to determine the next configuration from a given configuration, since it involves only multiplication and addition of matrices after deciding the spiking transition vector.

Link Prediction in a Modified Heterogeneous Bibliographic Network

Researchers have discovered, in recent years, the advantages of modeling complex systems using heterogeneous information networks. These networks are comprised of heterogeneous sets of nodes and edges that better represent the different entities and relationships often found in the real world. Although heterogeneous networks provide a richer semantic view of the data, the added complexity makes it difficult to directly apply existing techniques that work well on homogeneous networks. In this paper, we propose a graph modification process that alters an existing heterogeneous bibliographic network into another network, with the purpose of highlighting the important relations in the bibliographic network. Several importance scores, some adopted from existing work and others defined in this work, are then used to measure the importance of links in the modified network. The link prediction problem is studied on the modified network by implementing a random walk-based algorithm on the network. The importance scores and the structure of the modified graph are used to guide a random walker towards relevant parts of the graph, i.e. towards nodes to which new links will be created in the future. The different properties of the proposed algorithm are evaluated experimentally on a real world bibliographic network, the DBLP. Results show that the proposed method outperforms the state-of-the-art supervised technique as well as various approaches based on topology and node attributes.

Sequential spiking neural P systems with structural plasticity based on max/min spike number

AbstractSpiking neural P systems (in short, SNP systems) are parallel, distributed, and nondeterministic computing devices inspired by biological spiking neurons. Recently, a class of SNP systems known as SNP systems with structural plasticity (in short, SNPSP systems) was introduced. SNPSP systems represent a class of SNP systems that have dynamism applied to the synapses, i.e. neurons can use plasticity rules to create or remove synapses. In this work, we impose the restriction of sequentiality on SNPSP systems, using four modes: max, min, max-pseudo-, and min-pseudo-sequentiality. We also impose a normal form for SNPSP systems as number acceptors and generators. Conditions for (non)universality are then provided. Specifically, acceptors are universal in all modes, while generators need a nondeterminism source in two modes, which in this work is provided by the plasticity rules.

Simulating Spiking Neural P Systems Without Delays Using GPUs

We present in this paper our work regarding simulating a type of P system known as a spiking neural P system (SNP system) using graphics processing units (GPUs). GPUs, because of their architectural optimization for parallel computations, are well-suited for highly parallelizable problems. Due to the advent of general purpose GPU computing in recent years, GPUs are not limited to graphics and video processing alone, but include computationally intensive scientific and mathematical applications as well. Moreover P systems, including SNP systems, are inherently and maximally parallel computing models whose inspirations are taken from the functioning and dynamics of a living cell. In particular, SNP systems try to give a modest but formal representation of a special type of cell known as the neuron and their interactions with one another. The nature of SNP systems allowed their representation as matrices, which is a crucial step in simulating them on highly parallel devices such as GPUs. The highly parallel nature of SNP systems necessitate the use of hardware intended for parallel computations. The simulation algorithms, design considerations, and implementation are presented. Finally, simulation results, observations, and analyses using an SNP system that generates all numbers in

Spiking neural P system simulations on a high performance GPU platform

\mathbb N

Time after Time: Notes on Delays in Spiking Neural P Systems

- {1} are discussed, as well as recommendations for future work.

PROJECTION Algorithm for Motif Finding on GPUs

In this paper we present our results in adapting a Spiking Neural P system (SNP system) simulator to a high performance graphics processing unit (GPU) platform. In particular, we extend our simulations to larger and more complex SNP systems using an NVIDIA Tesla C1060 GPU. The C1060 is manufactured for high performance computing and massively parallel computations, matching the maximally parallel nature of SNP systems. Using our GPU accelerated simulations we present speedups of around 200× for some SNP systems, compared to CPU only simulations.

Relating Computations in Non-cooperative Transition P Systems and Evolution-Communication P Systems with Energy

Spiking Neural P systems, SNP systems for short, are biologically inspired computing devices based on how neurons perform computations. SNP systems use only one type of symbol, the spike, in the computations. Information is encoded in the time differences of spikes or the multiplicity of spikes produced at certain times. SNP systems with delays (associated with rules) and those without delays are two of several Turing complete SNP system variants in literature. In this work we investigate how restricted forms of SNP systems with delays can be simulated by SNP systems without delays. We show the simulations for the following spike routing constructs: sequential, iteration, join, and split.