Abstract
In biological data, it is often the case that objects are described in two or more representations. In order to perform classification based on such data, we have to combine them in a certain way. In the context of kernel machines, this task amounts to mix several kernel matrices into one. In this paper, we present two ways to mix kernel matrices, where the mixing weights are optimized to minimize the cross validation error. In bacteria classification and gene function prediction experiments, our methods significantly outperformed single kernel classifiers in most cases.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Kolcz, A. and Allinson, N.M.:Application of the CMAC input encoding scheme in the N-tuple approximation network, IEE Proc.Comput.Digital Techniques, 141 (1994), 177–183.
He, C. Xu, L. and Zhang, Y.:Learning convergence of CMAC algorithm, Neural Processing Letters 14 (2001), 61–74.
Chiang, C.-T. and Lin, C.-S.:CMAC with general basis functions, Neural Networks, 9 (1996), 1199–1211.
Lin, C.-S. and Chiang, C.-T.:Learning convergence of CMAC technique, IEEE Trans. on Neural Networks, 8 (1997), 1281–1292.
Albus, J.S.:A new approach to manipulator control:The cerebellar model articulation controller (CMAC), Trans.ASME, J.Dyanmic Syst., Meas.Contr., 97 (1975), 220–227.
Albus, J.S.:Data storage in the cerebellar model articulation controller(CMAC), Trans. ASME J.Dynamics Syst.Means.Contr., 97 (1975), 228–233.
Chang, G.-C., Lub, J.-J., Liao, G.-D., Lai, J.-S., Cheng, C.-K., Kuo, B.-L.and Kuo, T.-S.: A neuro-control system for the knee joint position control with quadriceps stimulation, IEEE Trans.Rehab.Eng., 5 (1997), 2–11.
Ker, J.-S., Kuo, Y.-H. and Liu, B.-D.:Hardware realization of higher-order CMAC model for color calibration, Proc.of IEEE International Conference on Neural Networks, Perth, WA, Austrialia (11/27/1995–12/01/1995), (1656–1661).
Koo, K.-M. and Kim, J.-H.:CMAC based control of nonlinear mechanical system, Proc. of the 1996 IEEE IECON 22nd International Conference on Industrial Electronics, Control, and Instrumentation, Taipei, Taiwan, Aug 5–10, (1996), 1954–1959.
Ljung, L. and Soderstrom, T.:Theory and Practice of Recursive Identification, The MIT Press, 1983, pp 16–21.
Liu, H., Xu, X. and Zhang, Z.:An improved CMAC neural network algorithm, Acta Automatica Sinica, 23 (1997), 482–488.
Parks, P.C. and Militzer, J.:Convergence properties of associative memory storage for learning control system, Automation and Remote Control, 50 (1989), 254–286.
Lane, S.H. Handelman, D.A. and Gelfand, J.J.:Theory and development of higher-order CMAC neural networks, IEEE Control Systems Magazine, 12 (1992), 23–30.
Manglevhedakar, S.:An adaptive hierarchical model for computer vision, Thesis, Louisiana State UNiv.1986.
Miller, W.T., Latham, P.J. and Scalera, S.M.:Bipedal Gait Adaptation for Walking with Dynamic Balance, Proc of the 1991 American Controls Conference, Boston, MA, 2 (1991), 1603–1608.
Miller, W.T., Glanz, F.H. and Kraft, L.G.:Application of a general learning algorithm to the control of robotic manipulators, Int.J.of Robotics Research, 6 (1987), 84–98.
Miller, W.T.:Real-time application of neural networks for sensor-based control of robots with vision, IEEE Transactions on Systems, Man and Cybernetics, 19 (1989), 825–831.
Miller, W.T., Hewes, R.P., Glanz, F.H. and Kraft, L.G.:Real-time dynamic control of an industrial manipulator using a neural-network-based learning controller, IEEE Trans. on robotics and automation, 6 (1990), 1–9.
Wu, X.:Matrix Theory, Tongji Universitiy Press, 1994.
Wong, Y.-F. and Siders, A.:Learning convergence in the cerebellar model articulation controller, IEEE Trans.on Neural Networks, 3, (1992), 115–121.
Wang, Z.-Q. Schiano, J.L. and Ginsberg, M.:Hash-Coding in CMAC Neural Networks, Proc.of IEEE International Conference on Neural Networks, Washington, DC, USA, June 3–6 (1996), 1698–1703.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Tsuda, K., Uda, S., Kin, T. et al. Minimizing the Cross Validation Error to Mix Kernel Matrices of Heterogeneous Biological Data. Neural Processing Letters 19, 63–72 (2004). https://doi.org/10.1023/B:NEPL.0000016845.36307.d7
Issue Date:
DOI: https://doi.org/10.1023/B:NEPL.0000016845.36307.d7