Spiking Neural System Research Articles

On Spiking Neural Membrane Systems with Neuron and Synapse Creation.

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.

A Layered Spiking Neural System for Classification Problems.

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.

A Time Series Forecasting Approach Based on Nonlinear Spiking Neural Systems.

Nonlinear spiking neural P (NSNP) systems are a recently developed theoretical model, which is abstracted by nonlinear spiking mechanism of biological neurons. NSNP systems have a nonlinear structure and the potential to describe nonlinear dynamic systems. Based on NSNP systems, a novel time series forecasting approach is developed in this paper. During the training phase, a time series is first converted to frequency domain by using a redundant wavelet transform, and then according to the frequency data, an NSNP system is automatically constructed and adaptively trained in frequency domain. Then, the well-trained NSNP system can automatically generate sequence data for future time as the prediction results. Eight benchmark time series data sets and two real-life time series data sets are utilized to compare the proposed approach with several state-of-the-art forecasting approaches. The comparison results demonstrate availability and effectiveness of the proposed forecasting approach.

Attitude control of an unmanned patrol helicopter based on an optimised spiking neural membrane system for use in coal mines

For the attitude control of unmanned helicopters used in the intelligent patrolling of coal mines, a spiking neural membrane system is introduced for attitude optimisation control. First, a geometry-based attitude dynamics model suitable for coal mine scenarios is constructed. Second, in accordance with the attitude dynamics model, an extended spiking neural membrane system (ESNMS) is constructed, and an optimised spiking neural membrane system (OSNMS) and accompanying algorithm are designed to optimise the ESNMS. Then, the attitude control performance of the developed system is theoretically analysed. Finally, through the simulation of a semiphysical experimental platform, trajectory tracking is effectively realised. Under normal and wind disturbance conditions, comparisons with the traditional synovium controller (TSC) and linear feedback controller (LFC) show that the performance of the designed OSNMS is greatly improved, and the experimental results show that the OSNMS has good stability and effectiveness.

Attitude control of an unmanned patrol helicopter based on an optimised spiking neural membrane system for use in coal mines

For the attitude control of unmanned helicopters used in the intelligent patrolling of coal mines, a spiking neural membrane system is introduced for attitude optimisation control. First, a geometr...

Sparse Hardware Embedding of Spiking Neuron Systems for Community Detection

We study the applicability of spiking neural networks and neuromorphic hardware for solving general opti- mization problems without the use of adaptive training or learning algorithms. We leverage the dynamics of Hopfield networks and spin-glass systems to construct a fully connected spiking neural system to generate synchronous spike responses indicative of the underlying community structure in an undirected, unweighted graph. Mapping this fully connected system to current generation neuromorphic hardware is done by embedding sparse tree graphs to generate only the leading-order spiking dynamics. We demonstrate that for a chosen set of benchmark graphs, the spike responses generated on a current generation neuromorphic processor can improve the stability of graph partitions and non-overlapping communities can be identified even with the loss of higher-order spiking behavior if the graphs are sufficiently dense. For sparse graphs, the loss of higher-order spiking behavior improves the stability of certain graph partitions but does not retrieve the known community memberships.

Sparse Temporal Encoding of Visual Features for Robust Object Recognition by Spiking Neurons

Robust object recognition in spiking neural systems remains a challenging in neuromorphic computing area as it needs to solve both the effective encoding of sensory information and also its integration with downstream learning neurons. We target this problem by developing a spiking neural system consisting of sparse temporal encoding and temporal classifier. We propose a sparse temporal encoding algorithm which exploits both spatial and temporal information derived from an spike-timing-dependent plasticity-based HMAX feature extraction process. The temporal feature representation, thus, becomes more appropriate to be integrated with a temporal classifier based on spiking neurons rather than with nontemporal classifier. The algorithm has been validated on two benchmark data sets and the results show the temporal feature encoding and learning-based method achieves high recognition accuracy. The proposed model provides an efficient approach to perform feature representation and recognition in a consistent temporal learning framework, which is easily adapted to neuromorphic implementations.

Event-Driven Continuous STDP Learning With Deep Structure for Visual Pattern Recognition.

Human beings can achieve reliable and fast visual pattern recognition with limited time and learning samples. Underlying this capability, ventral stream plays an important role in object representation and form recognition. Modeling the ventral steam may shed light on further understanding the visual brain in humans and building artificial vision systems for pattern recognition. The current methods to model the mechanism of ventral stream are far from exhibiting fast, continuous, and event-driven learning like the human brain. To create a visual system similar to ventral stream in human with fast learning capability, in this paper, we propose a new spiking neural system with an event-driven continuous spike timing dependent plasticity (STDP) learning method using specific spiking timing sequences. Two novel continuous input mechanisms have been used to obtain the continuous input spiking pattern sequence. With the event-driven STDP learning rule, the proposed learning procedure will be activated if the neuron receive one pre- or post-synaptic spike event. The experimental results on MNIST database show that the proposed method outperforms all other methods in fast learning scenarios and most of the current models in exhaustive learning experiments.

Probabilistic Deep Spiking Neural Systems Enabled by Magnetic Tunnel Junction

Deep Spiking Neural Networks are becoming increasingly powerful tools for cognitive computing platforms. However, most of the existing literature on such computing models are developed with limited insights on the underlying hardware implementation, resulting in area and power expensive designs. Although several neuromimetic devices emulating neural operations have been proposed recently, their functionality has been limited to very simple neural models that may prove to be inefficient at complex recognition tasks. In this work, we venture into the relatively unexplored area of utilizing the inherent device stochasticity of such neuromimetic devices to model complex neural functionalities in a probabilistic framework in the time domain. We consider the implementation of a Deep Spiking Neural Network capable of performing high accuracy and low latency classification tasks where the neural computing unit is enabled by the stochastic switching behavior of a Magnetic Tunnel Junction. Simulation studies indicate an energy improvement of $20\times$ over a baseline CMOS design in $45nm$ technology.

Modelling and verification of weighted spiking neural systems

This paper presents spiking neural P systems with weighted synapses, a class of distributed parallel neural-like computing models, abstracted from the way in which the complex system of neurons processes information and communicates to ensure a proper functioning of the brain. Neurons communicate with each other through synapses endowed with an integer weight denoting the number of synapses for each pair of connected neurons. We translate the spiking neural P systems with weighted synapses into a class of timed safety automata, proving that such a translation is formally correct. This relationship allows the verification of several kinds of properties, both qualitative and quantitative, using tools and techniques developed for timed automata.

Analysis of Chaotic Resonance in Izhikevich Neuron Model.

In stochastic resonance (SR), the presence of noise helps a nonlinear system amplify a weak (sub-threshold) signal. Chaotic resonance (CR) is a phenomenon similar to SR but without stochastic noise, which has been observed in neural systems. However, no study to date has investigated and compared the characteristics and performance of the signal responses of a spiking neural system in some chaotic states in CR. In this paper, we focus on the Izhikevich neuron model, which can reproduce major spike patterns that have been experimentally observed. We examine and classify the chaotic characteristics of this model by using Lyapunov exponents with a saltation matrix and Poincaré section methods in order to address the measurement challenge posed by the state-dependent jump in the resetting process. We found the existence of two distinctive states, a chaotic state involving primarily turbulent movement and an intermittent chaotic state. In order to assess the signal responses of CR in these classified states, we introduced an extended Izhikevich neuron model by considering weak periodic signals, and defined the cycle histogram of neuron spikes as well as the corresponding mutual correlation and information. Through computer simulations, we confirmed that both chaotic states in CR can sensitively respond to weak signals. Moreover, we found that the intermittent chaotic state exhibited a prompter response than the chaotic state with primarily turbulent movement.

Adaptive Inverse Control of Neural Spatiotemporal Spike Patterns With a Reproducing Kernel Hilbert Space (RKHS) Framework

The precise control of spiking in a population of neurons via applied electrical stimulation is a challenge due to the sparseness of spiking responses and neural system plasticity. We pose neural stimulation as a system control problem where the system input is a multidimensional time-varying signal representing the stimulation, and the output is a set of spike trains; the goal is to drive the output such that the elicited population spiking activity is as close as possible to some desired activity, where closeness is defined by a cost function. If the neural system can be described by a time-invariant (homogeneous) model, then offline procedures can be used to derive the control procedure; however, for arbitrary neural systems this is not tractable. Furthermore, standard control methodologies are not suited to directly operate on spike trains that represent both the target and elicited system response. In this paper, we propose a multiple-input multiple-output (MIMO) adaptive inverse control scheme that operates on spike trains in a reproducing kernel Hilbert space (RKHS). The control scheme uses an inverse controller to approximate the inverse of the neural circuit. The proposed control system takes advantage of the precise timing of the neural events by using a Schoenberg kernel defined directly in the space of spike trains. The Schoenberg kernel maps the spike train to an RKHS and allows linear algorithm to control the nonlinear neural system without the danger of converging to local minima. During operation, the adaptation of the controller minimizes a difference defined in the spike train RKHS between the system and the target response and keeps the inverse controller close to the inverse of the current neural circuit, which enables adapting to neural perturbations. The results on a realistic synthetic neural circuit show that the inverse controller based on the Schoenberg kernel outperforms the decoding accuracy of other models based on the conventional rate representation of neural signal (i.e., spikernel and generalized linear model). Moreover, after a significant perturbation of the neuron circuit, the control scheme can successfully drive the elicited responses close to the original target responses.

A Proposal for Hybrid Memristor-CMOS Spiking Neuromorphic Learning Systems

Recent research in nanotechnology has led to the practical realization of nanoscale devices that behave as memristors, a device that was postulated in the seventies by Chua based on circuit theoretical reasonings. On the other hand, neuromorphic engineering, a discipline that implements physical artifacts based on neuroscience knowledge, has related neural learning mechanisms to the operation of memristors. As a result, neuro-inspired learning architectures can be proposed that exploit nanoscale memristors for building very large scale systems with very dense synaptic-like memory elements. At present, the deep understanding of the internal mechanisms governing memristor operation is still an open issue, and the practical realization of very large scale and reliable ?memristive fabric? for neural learning applications is not a reality yet. However, in the meantime, researchers are proposing and analyzing potential circuit architectures that would combine a standard CMOS substrate with a memristive nanoscale fabric on top to realize hybrid memristor-CMOS neural learning systems. The focus of this paper is on one such architecture for implementing the very well established Spike-Timing-Dependent-Plasticity (STDP) learning mechanism found in biology. In this paper we quickly review spiking neural systems, STDP learning, and memristors, and propose a hybrid memristor-CMOS system architecture with the potential of implementing a large scale STDP learning spiking neural system. Such architecture would eventually allow to implement real-time brain-like processing learning systems with about neurons and synapses on one single Printed Circuit Board (PCB).

When less is more: Non-monotonic spike sequence processing in neurons

Event Abstract Back to Event When less is more: Non-monotonic spike sequence processing in neurons Hinrich Kielblock1, 2*, Birk Urmersbach1, Shuwen Chang3, Holger Taschenberger3 and Marc Timme1, 2 1 Max Planck Institute for Dynamics and Self-Organization, Network Dynamics Group, Germany 2 Berstein Center for Computational Neuroscience Göttingen, Germany 3 Max Planck Institute for Biophysical Chemistry, Membrane Biophysics Department, Germany The computational capabilities of neural circuits centrally rely on the input-output relations of single neurons. It is commonly accepted that neurons respond to inputs monotonically such that increasing the input implies increasing the output. Yet, most theoretical and experimental input-output studies have so far focused on continuous-time inputs, whereas most neurons communicate via exchanging electrical pulses (spikes) at discrete times. Here we show that the stationary response to regular spike sequences is typically non-monotonic such that increasing the input frequency to a neuron may decrease its output frequency. The underlying mechanism relies solely on a combination of the discrete nature of the communication by spikes and generically limited resources required for input sequence processing. As a consequence, this phenomenon universally emerges across a variety of spiking neural systems. It may support stabilizing the generation of spike sequences in neural circuits. Acknowledgements We thank D. Bibichkov and S. Schreiber for valuable discussions. Partially supported by the BMBF Germany under grant no. 01GQ1005B and by a grant from the Max Planck Society to Marc Timme. Keywords: excitability, locking, Neurons, networks and dynamical systems, spike sequence processing Conference: BC11 : Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting 2011, Freiburg, Germany, 4 Oct - 6 Oct, 2011. Presentation Type: Demonstration Topic: neurons, networks and dynamical systems (please use "neurons, networks and dynamical systems" as keywords) Citation: Kielblock H, Urmersbach B, Chang S, Taschenberger H and Timme M (2011). When less is more: Non-monotonic spike sequence processing in neurons. Front. Comput. Neurosci. Conference Abstract: BC11 : Computational Neuroscience & Neurotechnology Bernstein Conference & Neurex Annual Meeting 2011. doi: 10.3389/conf.fncom.2011.53.00163 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 22 Aug 2011; Published Online: 04 Oct 2011. * Correspondence: Mr. Hinrich Kielblock, Max Planck Institute for Dynamics and Self-Organization, Network Dynamics Group, Göttingen, Germany, hinrich@nld.ds.mpg.de Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Hinrich Kielblock Birk Urmersbach Shuwen Chang Holger Taschenberger Marc Timme Google Hinrich Kielblock Birk Urmersbach Shuwen Chang Holger Taschenberger Marc Timme Google Scholar Hinrich Kielblock Birk Urmersbach Shuwen Chang Holger Taschenberger Marc Timme PubMed Hinrich Kielblock Birk Urmersbach Shuwen Chang Holger Taschenberger Marc Timme Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

Performance/price estimates for cortex-scale hardware: A design space exploration

In this paper, we revisit the concept of virtualization. Virtualization is useful for understanding and investigating the performance/price and other trade-offs related to the hardware design space. Moreover, it is perhaps the most important aspect of a hardware design space exploration. Such a design space exploration is a necessary part of the study of hardware architectures for large-scale computational models for intelligent computing, including AI, Bayesian, bio-inspired and neural models. A methodical exploration is needed to identify potentially interesting regions in the design space, and to assess the relative performance/price points of these implementations. As an example, in this paper we investigate the performance/price of (digital and mixed-signal) CMOS and hypothetical CMOL (nanogrid) technology based hardware implementations of human cortex-scale spiking neural systems. Through this analysis, and the resulting performance/price points, we demonstrate, in general, the importance of virtualization, and of doing these kinds of design space explorations. The specific results suggest that hybrid nanotechnology such as CMOL is a promising candidate to implement very large-scale spiking neural systems, providing a more efficient utilization of the density and storage benefits of emerging nano-scale technologies. In general, we believe that the study of such hypothetical designs/architectures will guide the neuromorphic hardware community towards building large-scale systems, and help guide research trends in intelligent computing, and computer engineering.

Controlled perturbation-induced switching in pulse-coupled oscillator networks

Pulse-coupled systems such as spiking neural networks exhibit nontrivial invariant sets in the form of attracting yet unstable saddle periodic orbits where units are synchronized into groups. Heteroclinic connections between such orbits may in principle support switching processes in these networks and enable novel kinds of neural computations. For small networks of coupled oscillators, we here investigate under which conditions and how system symmetry enforces or forbids certain switching transitions that may be induced by perturbations. For networks of five oscillators, we derive explicit transition rules that for two cluster symmetries deviate from those known from oscillators coupled continuously in time. A third symmetry yields heteroclinic networks that consist of sets of all unstable attractors with that symmetry and the connections between them. Our results indicate that pulse-coupled systems can reliably generate well-defined sets of complex spatiotemporal patterns that conform to specific transition rules. We briefly discuss possible implications for computation with spiking neural systems.

Modeling of inhibition/excitation firing in olfactory bulb through spiking neurons

Spiking neural systems are based on biologically inspired neural models of computation since they take into account the precise timing of spike events and therefore are suitable to analyze dynamical aspects of neuronal signal transmission. These systems gained increasing interest because they are more sophisticated than simple neuron models found in artificial neural systems; they are closer to biophysical models of neurons, synapses, and related elements and their synchronized firing of neuronal assemblies could serve the brain as a code for feature binding and pattern segmentation. The simulations are designed to exemplify certain properties of the olfactory bulb (OB) dynamics and are based on an extension of the integrate-and-fire (IF) neuron, and the idea of locally coupled excitation and inhibition cells. We introduce the background theory to making an appropriate choice of model parameters. The following two forms of connectivity offering certain computational and analytical advantages, either through symmetry or statistical properties in the study of OB dynamics have been used: a) all-to-all coupling, b) receptive field style coupling. Our simulations showed that the inter-neuron transmission delay controls the size of spatial variations of the input and also smoothes the network response. Our IF extended model proves to be a useful basis from which we can study more sophisticated features as complex pattern formation, and global stability and chaos of OB dynamics.

Examining methods for estimating mutual information in spiking neural systems

Mutual information enjoys wide use in the computational neuroscience community for analyzing spiking neural systems. Its direct calculation is difficult because estimating the joint stimulus–response distribution requires a prohibitive amount of data. Consequently, several techniques have appeared for bounding mutual information that rely on less data. We examine two upper bound techniques and find that they are unreliable and can introduce strong assumptions about the neural code. We also examine two lower bounds, showing that they can be very loose and possibly bear little relation to the mutual information's actual value.