Abstract
Static pattern recognition requires a machine to classify an object on the basis of a combination of attributes and is typically performed using machine learning techniques such as support vector machines and multilayer perceptrons. Unusually, in this study, we applied a successful time-series processing neural network architecture, the echo state network (ESN), to a static pattern recognition task. The networks were presented with clamped input data patterns, but in this work, they were allowed to run until their output units delivered a stable set of output activations, in a similar fashion to previous work that focused on the behaviour of ESN reservoir units. Our aim was to see if the short-term memory developed by the reservoir and the clamped inputs could deliver improved overall classification accuracy. The study utilized a challenging, high dimensional, real-world plant species spectroradiometry classification dataset with the objective of accurately detecting one of the world’s top 100 invasive plant species. Surprisingly, the ESNs performed equally well with both unsettled and settled reservoirs. Delivering a classification accuracy of 96.60%, the clamped ESNs outperformed three widely used machine learning techniques, namely support vector machines, extreme learning machines and multilayer perceptrons. Contrary to past work, where inputs were clamped until reservoir stabilization, it was found that it was possible to obtain similar classification accuracy (96.49%) by clamping the input patterns for just two repeats. The chief contribution of this work is that a recurrent architecture can get good classification accuracy, even while the reservoir is still in an unstable state.
Similar content being viewed by others
References
Alexandre LA, Embrechts MJ. Reservoir size, spectral radius and connectivity in static classification problems. In: Alippi C, Polycarpou M, Panayiotou C, Ellinas G, editors. Artificial neural networks-ICANN 2009, vol. 5768. Berlin Heidelberg: Springer; 2009. p. 1015–24.
L. A. Alexandre, M. J. Embrechts, and J. Linton, “Benchmarking reservoir computing on time-independent classification tasks,” in International Joint Conference on Neural Networks, 2009. IJCNN 2009., pp. 89–93.
Bache K, Lichman M. UCI machine learning repository. Irvine, School of Information and Computer Sciences: University of California; 2013.
Bacic B. Echo state network for 3D motion pattern indexing: a case study on tennis forehands. In: Braunl T, McCane B, Rivera M, Yu X, editors. Image and video technology: 7th Pacific-rim Symposium, PSIVT 2015, Auckland, New Zealand, November 25–27, 2015, revised selected papers. Cham: Springer International Publishing; 2016. p. 295–306.
Bozhkov L, Koprinkova-Hristova P, Georgieva P. Reservoir computing for emotion valence discrimination from EEG signals. Neurocomputing. 2017;231:28–40.
Busing L, Schrauwen B, Legenstein R. Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons. Neural Comput. May 2010;22(5):1272–311.
Butcher JB, Day CR, Haycock PW, Verstraeten D, Schrauwen B. Defect detection in reinforced concrete using random neural architectures. Computer-Aided Civil and Infrastructure Engineering. 2014;29(3):191–207.
Chang C-C, Lin C-J. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol. 2011;2(3):27:1–27:27.
Cho MA, Sobhan I, Skidmore AK, de Leeuw J. Discriminating species using hyperspectral indices at leaf and canopy scales. In: ISPRS 2008 : Proceedings of the XXI congress: silk road for information from imagery: the International Society for Photogrammetry and Remote Sensing; 2008. p. 369–76.
Dutoit X, Schrauwen B, Campenhout JV, Stroobandt D, Brussel HV, Nuttin M. Pruning and regularization in reservoir computing. Neurocomputing. 2009;72(7–9):1534–46.
Edwards C, Taylor SL. A survey and strategic appraisal of rhododendron invasion and control in woodwood areas in Argyll and Bute. Forestry Commision Scotland: Perth Conservancy; 2008.
M. J. Embrechts, L. A. Alexandre, and J. D. Linton, “Reservoir computing for static pattern recognition,” in European Symposium on Artificial Neural Networks (ESANN) 2009, 2009.
Emmerich C, Reinhart R, Steil J. Recurrence enhances the spatial encoding of static inputs in reservoir networks. In: Diamantaras K, Duch W, Iliadis L, editors. Artificial neural networks-ICANN, vol. 6353. Berlin Heidelberg, 2010: Springer; 2010. p. 148–53.
Gaulton R, Olaya G, Wallington ED, Malthus TJ. Continuous cover forestry sensing in the UK? Quantifying Forest structure using remote sensing. In: Proceedings of ForestSAT Conference; 2005.
He KS, Rocchini D, Neteler M, Nagendra H. Benefits of hyperspectral remote sensing for tracking plant invasions. Divers Distrib. 2011;17(3):381–92.
Hoerl AE, Kennard RW. Ridge regression: biased estimation for Nonorthogonal problems. Technometrics. 1970;12(1):55–67.
G.-B. Huang, Q.-Y. Zhu, and C.-K. Siew, “Extreme learning machine: a new learning scheme of feedforward neural networks,” in Neural Networks, 2004. Proceedings. 2004 I.E. International Joint Conference on, 2004, vol. 2, pp. 985–990 vol. 2.
Jaeger H. The ‘echo state’ approach to analysing and training recurrent neural networks: Fraunhofer Institute for Autonomous Intelligent Systems; 2001.
H. Jaeger, “A tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the ‘echo state network’ approach,” Fraunhofer Institute for Autonomous Intelligent Systems (AIS), 4, 2013.
Lukosevicius M. A practical guide to applying echo state networks. In: Montavon G, Orr GB, Muller K-R, editors. Neural networks: tricks of the trade, vol. 7700. 2nd ed. Berlin Heidelberg: Eds. Springer; 2012. p. 659–86.
Matthews BW. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA) - Protein Structure. 1975;405(2):442–51.
Meftah B, Lezoray O, Benyettou A. Novel approach using Echo state networks for microscopic cellular image segmentation. Cogn Comput. 2016;8(2):237–45.
Montgomery DC, Peck EA, Vining CG. Introduction to linear regression analysis: Wiley; 1982.
Natschlager T, Maass W, Markram H. The ‘liquid Computer’: a novel strategy for real-time computing on time series. Special Issue on Foundations of Information Processing of TELEMATIK. 2002;8(1):39–43.
R. F. Reinhart and J. J. Steil, “Attractor-based computation with reservoirs for online learning of inverse kinematics,” in European Symposium on Artificial Neural Networks (ESANN) 2009, 2009.
Scardapane S, Uncini A. Semi-supervised Echo state networks for audio classification. Cogn Comput. 2016:1–11.
Sillin HO, Aguilera R, Shieh H-H, Avizienis AV, Aono M, Stieg AZ, Gimzewski JK. A theoretical and experimental study of neuromorphic atomic switch networks for reservoir computing. Nanotechnology. 2013;24(38):384004.
Taylor SL, Hill RA, Edwards C. Characterising invasive non-native Rhododendron Ponticum spectra signatures with spectroradiometry in the laboratory and field: potential for remote mapping. ISPRS J Photogramm Remote Sens. 2013;81(0):70–81.
Tong MH, Bickett AD, Christiansen EM, Cottrell GW. Learning grammatical structure with Echo state networks. Neural Netw. 2007;20(3):424–32.
Verstraeten D, Schrauwen B, D’Haene M, Stroobandt D. An experimental unification of reservoir computing methods. Neural Netw. 2007;20(3):391–403.
Wang L. Invasive species spread mapping using multi-resolution remote sensing data. Int Arch Photogramm Remote Sens Spat Inf Sci. 2008;37:135–42.
Williams F, Eschen R, Harris A, Djeddour D, Pratt C, Shaw RS, Varia S, Lamontagne-Godwin J, Thomas SE, Murphy ST. The economic cost of invasive non-native species on great Britain: CABI; 2010.
A. J. Wootton, C. R. Day, and P. W. Haycock, “Echo State Network Applications in Structrual Health Monitoring,” in Proceedings of the 53rd Annual Conference of The British Institute of Non-Destructive Testing (NDT 2014), 2014, pp. 289–300.
Acknowledgements
The authors thank NERC FSF for the provision of an equipment grant to S. L. Taylor, which was used to capture the original leaf sample spectroradiometry dataset.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
Adam Wootton declares that he has no conflict of interest. Sarah Taylor received a research grant from NERC FSF. Charles Day declares that he has no conflict of interest. Peter Haycock declares that he has no conflict of interest.
Funding
S. L. Taylor has received a research grant from NERC FSF, which was used to capture the original leaf sample spectroradiometry dataset.
Ethical Approval
This article does not contain any studies with human participants or animals performed by any of the authors.
Rights and permissions
About this article
Cite this article
Wootton, A.J., Taylor, S.L., Day, C.R. et al. Optimizing Echo State Networks for Static Pattern Recognition. Cogn Comput 9, 391–399 (2017). https://doi.org/10.1007/s12559-017-9468-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-017-9468-2