Dipartimento di Ingegneria Elettronica

Asynchronous Spiking Neural Networks

This research area concerns the development of an event-driven (or asynchronous) Spiking Neural Network (SNN) simulator, taking into account the most important biological neuron features, among which the spike latency (Fig. 1). Such neuronal feature represents a key factor for the information encoding. It has been conducted an accurate preliminary characterization of the spike latency by means of simulations carried out on the most accurate bio-realistic neuron model: the Hodgkin-Huxley model.

FIGURE 1. The red line indicates the spike latency as a function of the membrane potential V_m (red marked scale), or else of the current amplitude I_ext, equivalently, obtained by means of simulations in NEURON environment. The dashed blue line indicates the the spike latency behavior, that we have approximated to a rectangular hyperbola. In addition, the normalized scale S (i.e., neuron state) is reported (blue marked scale). Note that, below the S_th (i.e., spiking threshold) value, no spike can be generated (fading blue area).

Further features have been implemented in the model, such as subthreshold decay, refractory period, inhibitory effect, synaptic plasticity, etc.

An ad-hoc event-driven method has been implemented in order to allow continuous-time simulations and preserve the information coding properties of the spike latency. This approach is characterized by high precision and high computational efficiency at the same time.

Currently, the simulator is implemented in Matlab, allowing asynchronous simulations of network composed by over 10⁵ neurons. In the next future further improvements are planned: Java implementation, parallelization and hardware implementation.

It is also possible to apply some simple plasticity algorithms in order to emulate interesting global phenomena, such as the "Neuronal Group Selection" (Fig. 2) or the "jitter-reduction".

Figure 2. Formation of neuronal groups after a stimulation consisting of pseudo-random spike sequences.

Such a parallel systems can be used to handle the classic issues deal with artificial neural networks (e.g., pattern recognition), but also to model the biological neural circuitry. 

AWARDS

Best Paper Category, received at the International Conference "ACEEE, ACE 2012" (Amsterdam, NL) for the presented paper "Spiking neural networks as analog dynamical systems: basic paradigm and simple applications" (M. Salerno, G. Susi, A. D’Annessa, A. Cristini, Y. Sanfelice - June 2012). 

Best Poster Award, received at the 29th Annual Meeting of Circuit Theory Researchers (Padova University, IT), for the presented poster "Continuous-time Spiking Neural Networks: general paradigm and event-driven simulation". (M. Salerno, G. Susi, A. Cristini, M. Re, G.C. Cardarilli - June 2013). 

LIST OF PUBLICATIONS 

JOURNALS

Path multimodality in a Feedforward SNN module, using LIF with Latency model

Spiking Neural Networks As Continuous-Time Dynamical Systems: Fundamentals, Elementary Structures And Simple Applications
Mario Salerno, Gianluca Susi, Alessandro Cristini, Yari Sanfelice, Andrea D’Annessa
2013 ACEEE Int. J. on Information Technology, Vol. 3, No. 1, March 2013, pp. 80-89. ISSN:2158-0138, DOI:01.IJIT.3.1.1129 

CONFERENCE PAPERS

Spiking Neural Networks based on LIF with Latency: Simulation and Synchronization Effects

Gian Carlo Cardarilli, Alessandro Cristini, Luca Di Nunzio, Marco Re, Mario Salerno, Gianluca Susi

2013 IEEE Asilomar Conference on Signals, Systems, and Computers, 3-6 Nov. 2013, Pacific Grove, CA, USA, pp. 1838-1842. ISBN:978-1-4799-2388-5, DOI:10.1109/ACSSC.2013.6810620. IEEE CONFERENCE PUBLICATIONS.   

Spiking neural networks as analog dynamical systems: basic paradigm and simple applications
Mario Salerno, Gianluca Susi, Andrea D’Annessa, Alessandro Cristini, Yari Sanfelice
2012 Proc. of the 3rd Int. Conf. on advances in Computer Engineering, 2012, pp. 17-23. Publisher: ACEEE. ISBN:978-90-819067-8-4, DOI:02.ACE.2012.03.10  

Accurate latency characterization for very large asynchronous spiking neural networks
Mario Salerno, Gianluca Susi, Alessandro Cristini
2011 Proc. of the 4th Int. Conf. on Bioinformatics Models, Methods and Algorithms, 2011, pp. 116-124. Publisher: SciTePress. ISBN:978-989-8425-36-2. DOI:10.5220/0003134601160124

BOOK CHAPTERS

A Continuous-Time Spiking Neural Network Paradigm

Alessandro Cristini, Mario Salerno, Gianluca Susi

2015 Advances in Neural Networks: Computational and Theoretical Issues, Smart Innovation, Systems and Technologies, Vol. 37, pp. 49-60, 2015. ISBN:978-3-319-18163-9, ISSN:2190-3018, DOI:10.1007/978-3-319-18164-6_6

POSTERS

Spiking neural network-based character recognition exploiting different coding schemes

Event-driven simulation of continuous-time neural networks

Mario Salerno, Gianluca Susi, Alessandro Cristini, Marco Re, Gian Carlo Cardarilli
2014 30th Riunione Annuale dei Ricercatori di Elettrotecnica (ET2014), Sorrento, IT. DOI:10.13140/2.1.4182.3045 

Continuous-time Spiking Neural Networks: general paradigm and event-driven simulation
Mario Salerno, Gianluca Susi, Alessandro Cristini, Marco Re, Gian Carlo Cardarilli
2013 29th Riunione Annuale dei Ricercatori di Elettrotecnica (ET2013), Padova, IT. DOI:10.13140/2.1.2144.5443 

TECHNICAL REPORTS

A simple approach for different-scale CTNN simulations

Mario Salerno, Gianluca Susi, Alessandro Cristini, Gian Carlo Cardarilli, Marco Re 

Continuous-Time Neural Networks: paradigm and applications