Establishing the flow of information between two bio-inspired spiking neural networks

Abstract In this article, four bio-inspired spiking neural networks (emitter1&2, receiver1&2) were presented. Using the proposed brain-compatible learning, spiking networks were trained with spike-based unsupervised weight optimization to recognize handwritten digits, capital letters, YALE, and ORL datasets. Recent experimental reports have proven that effective neuronal interactions are affected by neuronal synchronization. Therefore, by preserving synchronization between emitters and receivers, the effective connection between them was established. Then, transfer entropy was used to quantify the exchanged information between emitter1-receiver1 and emitter2-receiver2. We proved that depending on the synchronization metric between emitter and receiver, information of emitter could be transmitted to receiver network. With these prerequisites, receivers were fed via the transmitted information of emitters without training. The remarkable result was that receiver1 and receiver2 achieved 70.23% and 84.97% recognition accuracy, respectively, without being trained for the handwritten digits and YALE faces. This means that we hacked 78.38% of the information of emitter1 and transmitted them into receiver1 (also 88.79% of emitter2 information was transmitted to receiver2). Thus, receivers learned extra information without training, which was guided solely by the information provided by emitters. In this paper, for the first time, we were able to bypass the training process of the spiking networks.

[1]  Wai Keung Wong,et al.  Robust Discriminant Regression for Feature Extraction , 2018, IEEE Transactions on Cybernetics.

[2]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[3]  S. Yoo,et al.  Non-Invasive Brain-to-Brain Interface (BBI): Establishing Functional Links between Two Brains , 2013, PloS one.

[4]  Mohammad Teshnehlab,et al.  Face Recognition Using Convolutional Neural Network and Simple Logistic Classifier , 2014 .

[5]  Yurong Liu,et al.  A survey of deep neural network architectures and their applications , 2017, Neurocomputing.

[6]  Yuan Yan Tang,et al.  Robust Face Recognition via Minimum Error Entropy-Based Atomic Representation , 2015, IEEE Transactions on Image Processing.

[7]  Yong Zhang,et al.  A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[8]  Li-Lian Wang,et al.  A Review of Prolate Spheroidal Wave Functions from the Perspective of Spectral Methods , 2017 .

[9]  M. Kossut,et al.  Reduction of GABAA receptor binding of [3H]muscimol in the barrel field of mice after peripheral denervation: transient and long-lasting effects , 2004, Experimental Brain Research.

[10]  Liang Zhao,et al.  Dimensionality reduction with the k-associated optimal graph applied to image classification , 2013, 2013 IEEE International Conference on Imaging Systems and Techniques (IST).

[11]  Alfréd Rényi,et al.  Probability Theory , 1970 .

[12]  Gustavo Deco,et al.  Optimal Information Transfer in the Cortex through Synchronization , 2010, PLoS Comput. Biol..

[13]  Ting Liu,et al.  Recent advances in convolutional neural networks , 2015, Pattern Recognit..

[14]  Konstantina S. Nikita,et al.  Parameter identification for a local field potential driven model of the Parkinsonian subthalamic nucleus spike activity , 2012, Neural Networks.

[15]  Cuiming Zou,et al.  Robust signal recovery using the prolate spherical wave functions and maximum correntropy criterion , 2018 .

[16]  G. Antunes,et al.  AMPA receptor trafficking and its role in heterosynaptic plasticity , 2018, Scientific Reports.

[17]  Jing Wang,et al.  A Brain-to-Brain Interface for Real-Time Sharing of Sensorimotor Information , 2013, Scientific Reports.

[18]  Yasuo Kuniyoshi,et al.  Comparison of nonlinear Granger causality extensions for low-dimensional systems. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[19]  Jian Yang,et al.  A New Discriminative Sparse Representation Method for Robust Face Recognition via $l_{2}$ Regularization , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[20]  Schreiber,et al.  Measuring information transfer , 2000, Physical review letters.

[21]  Jianwei Zhao,et al.  A novel algorithm of extended neural networks for image recognition , 2015, Eng. Appl. Artif. Intell..

[22]  Pablo A. Parrilo,et al.  The Convex Geometry of Linear Inverse Problems , 2010, Foundations of Computational Mathematics.

[23]  S. Strogatz,et al.  Stability of incoherence in a population of coupled oscillators , 1991 .

[24]  Golomb,et al.  Dynamics of globally coupled inhibitory neurons with heterogeneity. , 1993, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[25]  Jinkuan Wang,et al.  Sparse locality preserving discriminative projections for face recognition , 2017, Neurocomputing.

[26]  Bipin Kumar Tripathi,et al.  On the complex domain deep machine learning for face recognition , 2017, Applied Intelligence.

[27]  Teng Long,et al.  Robust non-homogeneity detection algorithm based on prolate spheroidal wave functions for space-time adaptive processing , 2013 .

[28]  Weifeng Liu,et al.  Correntropy: Properties and Applications in Non-Gaussian Signal Processing , 2007, IEEE Transactions on Signal Processing.

[29]  Robert A. Nawrocki,et al.  A Mini Review of Neuromorphic Architectures and Implementations , 2016, IEEE Transactions on Electron Devices.

[30]  Karim Faez,et al.  A new approach to detect the coding rule of the cortical spiking model in the information transmission , 2018, Neural Networks.

[31]  P. Fries.  A mechanism for cognitive dynamics: neuronal communication through neuronal coherence , 2005, Trends in Cognitive Sciences.

[32]  Jiashu Zhang,et al.  Discriminant Locality Preserving Projections Based on L1-Norm Maximization , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[33]  Qing Chen,et al.  Biological modelling of a computational spiking neural network with neuronal avalanches , 2017, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[34]  N. Logothetis.  The Underpinnings of the BOLD Functional Magnetic Resonance Imaging Signal , 2003, The Journal of Neuroscience.

[35]  Bijan Pesaran,et al.  Investigating large-scale brain dynamics using field potential recordings: analysis and interpretation , 2018, Nature Neuroscience.

[36]  D. McCormick,et al.  Comparative electrophysiology of pyramidal and sparsely spiny stellate neurons of the neocortex. , 1985, Journal of neurophysiology.

[37]  Anders Lansner,et al.  Non-commercial Research and Educational Use including without Limitation Use in Instruction at Your Institution, Sending It to Specific Colleagues That You Know, and Providing a Copy to Your Institution's Administrator. All Other Uses, Reproduction and Distribution, including without Limitation Comm , 2022 .

[38]  Jing Wang,et al.  Generalized 2-D Principal Component Analysis by Lp-Norm for Image Analysis , 2016, IEEE Transactions on Cybernetics.

[39]  Nicolas Brunel,et al.  Encoding of Naturalistic Stimuli by Local Field Potential Spectra in Networks of Excitatory and Inhibitory Neurons , 2008, PLoS Comput. Biol..

[40]  Robert E. Hampson,et al.  Donor/recipient enhancement of memory in rat hippocampus , 2013, Front. Syst. Neurosci..

[41]  John Rinzel,et al.  Synchrony measures for biological neural networks , 1995, Biological Cybernetics.

[42]  Jiang-Shu Wei,et al.  A New Sparse Representation Classifier (SRC) Based on Probability Judgement Rule , 2016, 2016 International Conference on Information System and Artificial Intelligence (ISAI).

[43]  Jiangshe Zhang,et al.  Softmax Discriminant Classifier , 2011, 2011 Third International Conference on Multimedia Information Networking and Security.

[44]  Giulio Ruffini,et al.  Conscious Brain-to-Brain Communication in Humans Using Non-Invasive Technologies , 2015, Brain Stimulation.

[45]  A. Taub,et al.  Oscillations Synchronize Amygdala-to-Prefrontal Primate Circuits during Aversive Learning , 2017, Neuron.

[46]  Ran He,et al.  Maximum Correntropy Criterion for Robust Face Recognition , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[47]  Thomas R. Shultz,et al.  Coupled feedback loops maintain synaptic long-term potentiation: A computational model of PKMzeta synthesis and AMPA receptor trafficking , 2017, PLoS Comput. Biol..