Bio-Inspired Temporal-Decoding Network Topologies for the Accurate Recognition of Spike Patterns

  • Gianluca Susi University of Rome, "Tor Vergata"; Department of Electronic Engineering, Department of Civil Engineering and Computer Science.
Keywords: Temporal coding, Neuronal modelling, Spiking Neural Network (SNN), Latency, Pattern recognition, Classification, Coincidence detection.


In this paper will be presented simple and effective temporal-decoding network topologies, based on a neuron model similar to the classic Leaky Integrate-and-Fire, but including the spike latency effect, a neuron property able to take into account that the firing of a given neuron is not instantaneous, but it occurs after a continuous-time delay depending on the inner state. These structures are able to detect spike sequences composed of pulses belonging to neuron ensembles, exploiting basic biological neuron mechanisms. According to the biological counterpart, with these structures is possible to achieve a high temporal accuracy, but also deal with the natural variability present in spike trains. In addition, the connection of these neural structures at a higher level make possible to afford some pattern recognition problems, operating a distributed and parallel input data processing.

Author Biography

Gianluca Susi, University of Rome, "Tor Vergata"; Department of Electronic Engineering, Department of Civil Engineering and Computer Science.
Gianluca Susi received a PhD in "Sensor and learning system engineering" in 2012 from the Department of Electronic Engineering, University of Rome "Tor Vergata".
He is currently adjunct professor (professore a contratto) of Electrical Engineering at the University of Rome "Tor Vergata".
His research activity is proved by papers concerning Spiking Neural Networks (SNNs), Audio Engineering and Brain Computer Interface (BCI). For the publications related to the SNN field, he has received national and international awards.
He is member of international scientific societies and reviewer for some international scientific journals. He is coordinator member and lecturer of the MIS (Master programme in Audio Engineering), University of Rome "Tor Vergata".


(1) Larson E, Perrone BP, Sen K, Billimoria CP, A robust and biologically plausible spike pattern recognition network. The Journal of Neuroscience, 2010. 30(46): p.15566 –15572.

(2) Paninski L , Pillow J , Lewi J, Statistical models for neural encoding, decoding, and optimal stimulus design. Progress in Brain Research 2007;165:493-507.

(3) Donoghue J, Connecting cortex to machines: recent advances in brain interfaces. Nature Neuroscience 5, pp. 1085–1088.

(4) Gütig, R, Sompolinsky H, The tempotron: a neuron that learns

spike timing-based decisons. Neuroscience (Nature), 2006.

(5) Panzeri S, Ince RAA, Diamond ME, Kayser C, Reading spike timing without a clock: intrinsic decoding of spike trains. Phylosophical transactions B, , The royal society publishing, 2014.

(6) Dhoble K, Nuntalid N, Indiveri G and Kasabov N. Online Spatio-Temporal Pattern Recognition with Evolving Spiking Neural Networks utilising Address Event Representation, Rank Order, and Temporal Spike Learning. Neural Networks (IJCNN), International Joint Conference on.

IEEE, 2012.

(7) Gautrais J, Thorpe S. Rate coding versus temporal order coding: a theoretical approach. Biosystems, Vol 48, Nov 1998, Pages 57–65.

(8) Rieke F, Warland D, van Steveninck RdR. Spikes: Exploring the neural code. MIT Press Cambridge, 1999.

(9) Morrison A, Diesmann M, Gerstner W, Phenomenological models of synaptic plasticity based on spike timing. Biological Cybernetics, vol. 98, no. 6, pp. 459–478, 2008.

(10) Brader J, Senn W, Fusi S, Learning real-world stimuli in a neural network with spike-driven synaptic dynamics. Neural computation, vol. 19, no. 11, pp. 2881–2912, 2007.

(11) Salerno M, Susi G, Cristini A, Accurate latency characterization for very large asynchronous spiking neural networks. 4th Int. Conf. on Bioinformatics Models, Methods and Algorithms, 2011.

(12) Cardarilli GC, Cristini A, Di Nunzio L, Re M, Salerno M, Susi G, Spiking Neural Networks based on LIF with Latency: Simulation and Synchronization Effects. 2013 IEEE Asilomar Conference on Signals, Systems, and Computers, 3-6 Nov 2013, Pacific Grove, CA, USA, pp. 1838-1842.

(13) Cristini A, Salerno M, Susi G, A Continuous-time Spiking Neural Network Paradigm. Advances in Neural Networks: Computational and Theoretical Issues - Smart Innovation, Systems and Technologies, vol. 37, pp. 49-60. Springer, 2015.

(14) Sutskever I, Vinyals O, VL Quoc, Sequence to Sequence Learning with Neural Networks. NIPS conference, 2014.

(15) Panchev C, Wermter S, Temporal sequence detection with spiking neurons: towards recognizing robot language instructions. Connection science. Taylor Francis, 2006.

(16) Gansel KS, Singer W, Detecting multineuronal temporal patterns in parallel spike trains. Frontiers in Neuroinformatics (2012); 6: 18.

(17) Salerno M, Susi G, Cristini A, Sanfelice Y, D’Annessa A, Spiking neural networks as continuous-time dynamical systems: fundamentals, elementary structures and simple applications. ACEEE Int. J. on Information Technology, Vol. 3, No. 1, Mar 2013, pp. 80-89.

(18) Gerstner W and Kistler WM, Spiking Neuron Models - Single Neurons, Populations, Plasticity. Cambridge University Press, 2002.

(19) Ventura, V, Spike Train Decoding without Spike Sorting. Neural Computation , Vol 20,4. MIT press, 2008.

(20) Gerstner W, Kistler WM, Naud R Paninski L, Neuronal Dynamics, From single neurons to networks and models of cognition. Cambridge University Press, 2014.