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

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.

[1]  Liam Paninski,et al.  Statistical models for neural encoding, decoding, and optimal stimulus design. , 2007, Progress in brain research.

[2]  Wulfram Gerstner,et al.  Phenomenological models of synaptic plasticity based on spike timing , 2008, Biological Cybernetics.

[3]  Stefan Wermter,et al.  Temporal sequence detection with spiking neurons: towards recognizing robot language instructions , 2006, Connect. Sci..

[4]  Walter Senn,et al.  Learning Real-World Stimuli in a Neural Network with Spike-Driven Synaptic Dynamics , 2007, Neural Computation.

[5]  Valérie Ventura,et al.  Spike Train Decoding Without Spike Sorting , 2008, Neural Computation.

[6]  Wolf Singer,et al.  Detecting Multineuronal Temporal Patterns in Parallel Spike Trains , 2012, Front. Neuroinform..

[7]  Kamal Sen,et al.  A Robust and Biologically Plausible Spike Pattern Recognition Network , 2010, The Journal of Neuroscience.

[8]  John P. Donoghue,et al.  Connecting cortex to machines: recent advances in brain interfaces , 2002, Nature Neuroscience.

[9]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[10]  William Bialek,et al.  Spikes: Exploring the Neural Code , 1996 .

[11]  Gian Carlo Cardarilli,et al.  Spiking neural networks based on LIF with latency: Simulation and synchronization effects , 2013, 2013 Asilomar Conference on Signals, Systems and Computers.

[12]  Giacomo Indiveri,et al.  Online spatio-temporal pattern recognition with evolving spiking neural networks utilising address event representation, rank order, and temporal spike learning , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[13]  Wulfram Gerstner,et al.  Neuronal Dynamics: From Single Neurons To Networks And Models Of Cognition , 2014 .

[14]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[15]  Alessandro Cristini,et al.  Spiking Neural Networks As Continuous-Time Dynamical Systems: Fundamentals, Elementary Structures And Simple Applications , 2013 .

[16]  H. Sompolinsky,et al.  The tempotron: a neuron that learns spike timing–based decisions , 2006, Nature Neuroscience.

[17]  Alessandro Cristini,et al.  A Continuous-Time Spiking Neural Network Paradigm , 2015, Advances in Neural Networks.

[18]  J Gautrais,et al.  Rate coding versus temporal order coding: a theoretical approach. , 1998, Bio Systems.

[19]  Alessandro Cristini,et al.  Accurate Latency Characterization for Very Large Asynchronous Spiking Neural Networks , 2011, BIOINFORMATICS.

[20]  Stefano Panzeri,et al.  Reading spike timing without a clock: intrinsic decoding of spike trains , 2014, Philosophical Transactions of the Royal Society B: Biological Sciences.