Morphological learning in multicompartment neuron model with binary synapses

There is a vast amount of neurobiological evidence supporting the role of dendritic processing in neural computation. However, most of the neuromorphic chips designed have overlooked these research findings. Here, we present a neuron model with multiple nonlinear spatially sensitive dendrites. Location-dependent processing occurs in multiple dendritic compartments, where sparse binary synapses are formed by utilizing structural plasticity rule. This rule is a correlation-based learning scheme inspired by the Tempotron learning rule to form synaptic connections on the dendritic compartments. The performance of the model is compared with a lumped dendrite model as well as with other classifiers for spatiotemporal spike patterns. The results indicate that our biologically realistic multicompartment model using low resolution weights achieves about 4–5% higher accuracy than the lumped scheme and about 2% less accuracy than the Tempotron using high resolution weights, while with 4bit weights the Tempotron accuracy drops by 5% of our proposed method.

[1]  Shaista Hussain,et al.  Delay learning architectures for memory and classification , 2014, Neurocomputing.

[2]  Bernabé Linares-Barranco,et al.  A 128$\,\times$ 128 1.5% Contrast Sensitivity 0.9% FPN 3 µs Latency 4 mW Asynchronous Frame-Free Dynamic Vision Sensor Using Transimpedance Preamplifiers , 2013, IEEE Journal of Solid-State Circuits.

[3]  Bartlett W. Mel,et al.  Location-Dependent Excitatory Synaptic Interactions in Pyramidal Neuron Dendrites , 2012, PLoS Comput. Biol..

[4]  E. J. Nalos.  Neural theory and modeling, proceedings of the 1962 Ojai symposium , 1965 .

[5]  Shaista Hussain,et al.  Spike-timing dependent morphological learning for a neuron with nonlinear active dendrites , 2014, 2014 International Joint Conference on Neural Networks (IJCNN).

[6]  Subhrajit Roy,et al.  A current-mode spiking neural classifier with lumped dendritic nonlinearity , 2015, 2015 IEEE International Symposium on Circuits and Systems (ISCAS).

[7]  Shaista Hussain,et al.  Morphological learning: Increased memory capacity of neuromorphic systems with binary synapses exploiting AER based reconfiguration , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

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

[9]  Bartlett W. Mel,et al.  Impact of Active Dendrites and Structural Plasticity on the Memory Capacity of Neural Tissue , 2001, Neuron.

[10]  Shaista Hussain,et al.  Learning Spike Time Codes Through Morphological Learning With Binary Synapses , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[11]  Andre van Schaik,et al.  Asynchronous Binaural Spatial Audition Sensor With 2$\,\times\,$64$\,\times\,$4 Channel Output , 2014, IEEE Transactions on Biomedical Circuits and Systems.

[12]  Arindam Basu,et al.  Transistor channel dendrites implementing HMM classifiers , 2007, 2007 IEEE International Symposium on Circuits and Systems.

[13]  Shaista Hussain,et al.  Hardware-Amenable Structural Learning for Spike-Based Pattern Classification Using a Simple Model of Active Dendrites , 2014, Neural Computation.

[14]  J. Magee.  Dendritic integration of excitatory synaptic input , 2000, Nature Reviews Neuroscience.