Abstract
Computer algorithms that match human performance in recognizing written text or spoken conversation remain elusive. The reasons why the human brain far exceeds any existing recognition scheme to date in the ability to generalize and to extract invariant characteristics relevant to category matching are not clear. However, it has been postulated that the dynamic distribution of brain activity (spatiotemporal activation patterns) is the mechanism by which stimuli are encoded and matched to categories. This research focuses on supervised learning using a trajectory based distance metric for category discrimination in an oscillatory neural network model. Classification is accomplished using a trajectory based distance metric. Since the distance metric is differentiable, a supervised learning algorithm based on gradient descent is demonstrated. Classification of spatiotemporal frequency transitions and their relation to a priori assessed categories is shown along with the improved classification results after supervised training. The results indicate that this spatiotemporal representation of stimuli and the associated distance metric is useful for simple pattern recognition tasks and that supervised learning improves classification results.
Similar content being viewed by others
References
Burwick T (2006) Oscillatory networks: pattern recognition without a superposition catastrophe. Neural Comput 18: 356–380
Cesmeli E, Lindsey DT, Wang DL (2002) An oscillatory correlation model of visual motion analysis. Percept Psychophys 64(8): 1191–1217
Dauce E, Quoy M, Doyon B (2002) Resonant spatiotemporal learning in large random recurrent networks. Biol Cybern 87: 185–198
Eckes C, Triesch J, Malsburg C (2006) Analysis of cluttered scenes using and elastic matching approach for stereo images. Neural Comput 18: 1441–1471
Ernst U, Pawelzik K, Geisel T (1998) Delay-induced multistable synchronization of biological oscillators. Phys Rev E 57(2): 2150–2162
Freeman WJ (1975) Mass action in the nervous system. Academic Press, New York
Freeman WJ (2003) Evidence from human scalp electroencephalograms of global chaotic itinerancy. Chaos 13(3): 1067–1077
Freeman WJ, Rogers LJ (2003) A neurobiological theory of meaning in perception. part v: multicortical patterns of phase modulation in gamma EEG. Int J Bifurcat Chaos 13(10): 2867–2887
Freeman WJ (2006) Origin, structure, and role of background EEG activity. part 4: neural frame simulation. Clin Neurophysiol 117: 572–589
Freeman WJ, Holmes MD, West GA, Vanhatalo S (2006) Fine spatiotemporal structure of phase in human intracranial EEG. Clin Neurophysiol 117: 1228–1243
Frith CD, Friston KJ (1996) The role of the thalamus in “Top Down” modulation of attention to sound. NeuroImage 4(3): 210–215
Gevins AS, Cutillo BA, Smith ME (1995) Regional modulation of high resolution evoked potentials during verbal and non-verbal matching tasks. Electroencephalogr Clin Neurophysiol 94: 129–147
Gray C, Singer W (1989) Stimulus specific neural oscillations in orientation columns of cat visual cortex. Proc Natl Acad Sci USA 86: 1698–1702
Gulick WL, Gescheider GA, Frisnia RD (1989) Hearing physiological acoustics, neural coding, and psychoacoustics. Oxford University Press, New York
Hodgkin A, Huxley A (1952) A quantitative description of membrane current and its application to conduction and excitation in nerve. J Phys 117: 500–544
Hoppensteadt FC, Izhikevich EM (1996a) Synaptic organizations and dynamical properties of weakly connected neural oscillators I. Analysis of a canonical model. Biol Cybern 75: 117–127
Hoppensteadt FC, Izhikevich EM (1996b) Synaptic organizations and dynamical properties of weakly connected neural oscillators II. Learning phase information. Biol Cybern 75: 129–135
Hoppensteadt FC, Izhikevich EM (1997) Weakly connected neural networks. Springer, Heidelberg
Izhikevich EM, Hoppensteadt FC (2003) Slowly coupled oscillators: phase dynamics and synchronization. SIAM J Appl Math 63(6): 1935–1953
Izhikevich EM (2001) Resonate-and-fire neurons. Neural Netw 14: 883–894
Jansen BH, Miller VH, Mavrofrides DC, Stegink-Jansen CW (2003) Multidimensional EMG-based assessment of walking dynamics. IEEE Trans Neural Syst Rehabil Eng 11(3): 294–300
Kazanovich Y, Borisyuk R (2006) An oscillatory neural model of multiple object tracking. Neural Comput 18: 1413–1440
Kelso JA (1995) Dynamic patterns: the self-organization of brain and behavior. The MIT Press, Cambridge
Kuramoto Y (1994) Chemical oscillations, waves, and turbulence. Springer, Berlin
Lehmann D (1977) The EEG as scalp field distribution in EEG informatics. In: Remond A (eds) A didactic review of methods and applications of EEG data processing. Elsevier/North-Holland Biomedical Press, Amsterdam, pp 365–384
Maistrenko YL, Lysyansky B, Hauptmann C, Burylko O, Tass PA (2007) Multistability in the Kuramoto model with synaptic plasticity. Phys Rev E 75(66207): 1–8
Masuda N, Doiron B, Longtin A, Aihara K (2005) Coding of temporally varying signals in networks of spiking neurons with global delayed feedback. Neural Comput 17: 2139–2175
Morris C, Lecar H (1981) Voltage oscillations in the barnacle giant muscle fiber. Biophys J 35: 193–213
Ohde RN, Ochs MT (1996) The effect of segment duration on the perceptual integration of nasals for adult and child speech. J Acoust Soc Am 100(4): 2486–2499
Pfurtscheller G, Neuper C, Flotzinger D, Pregenzer M (1997) EEG-based discrimination between imagination of right and left hand movement. Electroencephalogr Clin Neurophysiol 103: 642–651
Popovych OV, Hauptmann C, Tass P (2005) Effective desynchronization by nonlinear delayed feedback. Phys Rev Lett 94(164102): 1–4
Seliger P, Young SC, Tsimring LS (2002) Plasticity and learning in a network of coupled phase oscillators. Phys Rev E 65(041906): 1–7
Stevens KN, Blumstein SE, Glicksman L, Burton M, Kurowski K (1992) Acoustic and perceptual characteristics of voicing in fractives and fricative clusters. J Acoust Soc Am 91(5): 2979–2999
Tass P, Haken H (1996) Synchronization in networks of limit cycle oscillators. Z Phys B 100: 303–320
Tass P (1997) Phase and frequency shifts in a population of phase oscillators. Phys Rev E 56(2): 2048–2060
Tass P (1999) Phase resetting in medicine and biology. Springer, Berlin
Tass P (2002) Desynchronization of brain rhythms with soft phase-resetting techniques. Biol Cybern 87: 102–115
Tass P (2003) Stochastic phase resetting of stimulus-locked responses of two coupled oscillators: transient response clustering, synchronization, and desynchronization. Chaos 13(1): 364–376
Tass P (2004) Transmission of stimulus-locked responses in two oscillators with bistable coupling. Biol Cybern 91: 203–211
Tass P (2005) Phase resetting and transient desynchronization in networks of globally coupled phase oscillators with inertia. Phys D 211: 128–138
Tass P, Majtanik M (2006) Long-term anti-kindling effects of desynchronizing brain stimulation: a theoretical study. Biol Cybern 94: 58–66
van Wieringen A, Pols LC (1995) Discrimination of single and complex consonant-vowel and vowel-consonant-like formant transitions. J Acoust Soc Am 98(3): 1304–1312
von der Malsburg C, Buhmann J (1992) Sensory segmentation with coupled neural oscillators. Biol Cybern 67: 233–242
Wilson HR, Cowan JD (1972) Excitatory and inhibitory interactions in localized populations of model neurons. Biophys J Jan 12(1): 124
Yao Y, Freeman WJ (1990) Model of biological pattern recognition with spatially chaotic dynamics. Neural Netw 3: 153–170
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Miller, V.H., Jansen, B.H. Oscillatory neural network for pattern recognition: trajectory based classification and supervised learning. Biol Cybern 99, 459–471 (2008). https://doi.org/10.1007/s00422-008-0253-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00422-008-0253-x