Enlighten Publications

In this section

Spike-based analog-digital neuromorphic information processing system for sensor applications

Sánchez, G., Koickal, T. J., Sripad T A, A., Gouveia, L. C., Hamilton, A. and Madrenas, J. (2013) Spike-based analog-digital neuromorphic information processing system for sensor applications. In: 2013 IEEE International Symposium on Circuits and Systems (ISCAS), Beijing, China, 19-23 May 2013, pp. 1624-1627. (doi: 10.1109/ISCAS.2013.6572173)

Full text not currently available from Enlighten.

Publisher's URL: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6572173

Abstract

A spiking-neuron-based system that combines analog and digital multi-processor implementations for the bio-inspired processing of sensors is reported. This combination allows creating a powerful bio-inspired multiple-input sensor processing system for environment perception applications. The analog front-end encodes the input signal in a signed spike representation, which is further processed by means of a digital Spiking Neural Network (SNN) on a Single-Instruction Multiple-Data (SIMD) multiprocessor. The spike distribution for both systems is based on Address-Event Representation (AER) scheme, asynchronous for the Analog Pre-Processor (APP) and synchronous for the Digital Multi-Processor (DMP), synchronized by means of an AER transceiver. A proof-of-concept application of the system being able to process sensory information has been demonstrated. The system utilizes 30-neurons emulated by the DMP to process spike-encoded information provided by its analog counterpart, enabling the feature extraction of the input signal. The frequency detection capability of the system is experimentally reported.

Item Type:	Conference Proceedings
Keywords:	Spiking Neural Networks, Neuromorphic Circuits, SIMD, AER, Analog Spike Coder, Digital Emulation
Status:	Published
Refereed:	Yes
Glasgow Author(s) Enlighten ID:	Gouveia, Mr Luiz
Authors:	Sánchez, G., Koickal, T. J., Sripad T A, A., Gouveia, L. C., Hamilton, A., and Madrenas, J.
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering
College/School:	College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering

University Staff: Request a correction | Enlighten Editors: Update this record

References

[1] J. Madrenas and J. M. Moreno, "Strategies in SIMD Computing for neurons. Hence, only O6 fires and indicates that the input Complex Neural Bioinspired Applications," in AHS 2009. NASA/ESA signal is of maximum frequency detectable. After 400ms Conference on, 2009, pp. 376-381. (approx), the frequency of the input decreases. Hence the [2] M. J. Pearson et al, "Design and FPGA implementation of an embedded real-time biologically plausible spiking neural network corresponding levels of output neurons fire (O5 to O1) processor," in Field Programmable Logic and Applications, 2005. encoding the different frequency levels. This is because the International Conference on, 2005, pp. 582-585. membrane potential of lower block output neurons increase [3] G. Indiveri et al, "Neuromorphic silicon neuron circuits," Frontiers in due to excitatory connections and absence of inhibition from Neuroscience, vol. 5, 2011-May-31 2011. [4] R. Sarpeshkar, "Analog versus digital: extrapolating from electronics the immediate upper block. It can be noted that since the to neurobiology," Neural Comput., vol. 10, pp. 1601-1638, 1998. frequency decreases very fast around 400ms, there is a steep [5] I. S. Han, "Mixed-signal neuron-synapse implementation for largechange from O5 to O2 so no encoding appears in between. scale neural network," in BICS2004 2004, pp. 1-5. [6] J. Schemmel, J. Fieres, and K. Meier, "Wafer-scale integration of analog neural networks," in Neural Networks, 2008. IJCNN 2008. (IEEE World Congress on Computational Intelligence). IEEE International Joint Conference on, 2008, pp. 431-438. [7] S. Renaud et al, "Neuromimetic ICs with analog cores: an alternative for simulating spiking neural networks," in Circuits and Systems, 2007. ISCAS 2007. IEEE Int. Symposium on, 2007, pp. 3355-3358. [8] K. Boahen, "Point-to-point connectivity between neuromorphic chips using address event," in IEEE Trans Circuits Syst. II, Analog Digital Signal Process. vol. 47, 2000, pp. 416-434. [9] L. C. Gouveia et al, "An Asynchronous Spike Event Coding Scheme for Programmable Analog Arrays," Circuits and Systems I: Regular Papers, IEEE Transactions on, vol. 58, pp. 791-799, 2011. [10] A. Upegui et al, "The Perplexus bio-inspired reconfigurable circuit," in AHS 2007. Second NASA/ESA Conference on, 2007, pp. 600-605. [11] J. M. Moreno, J. Madrenas, and L. Kotynia, "Synchronous Digital Implementation of the AER Communication Scheme for Emulating Fig.7. Raster plot of neuron spikes. Large-Scale Spiking Neural Networks Models," in AHS 2009. NASA/ESA Conference on, 2009, pp. 189-196. [12] G. Sanchez, J. Madrenas, and J. Moreno, "Performance Evaluation V. CONCLUSIONS and Scaling of a Multiprocessor Architecture Emulating Complex SNN Algorithms," in Evolvable Systems: From Biology to In this work we presented the implementation of an analogHardware. vol. 6274: Springer Berlin Heidelberg, pp. 145-156, 2010. digital spiking-neuron-based system capable of processing [13] T. J. Koickal, A. Hamilton, S. L. Tan, J. A. Covington, J. W. Gardner, and T. C. Pearce, "Analog VLSI Circuit Implementation of multiple-input sensor information. For successful an Adaptive Neuromorphic Olfaction Chip," Circuits and Systems I: communication between analog and digital processors, a Regular Papers, IEEE Transactions on, vol. 54, pp. 60-73, 2007. transceiver has been developed and the maximum input

Deposit and Record Details

ID Code:	95813
Depositing User:	Mr Luiz Gouveia
Datestamp:	18 Aug 2014 11:10
Last Modified:	23 Sep 2021 23:01
Date of first online publication:	2013