Label propagation through neuronal synchrony

Semi-Supervised Learning (SSL) is a machine learning research area aiming the development of techniques which are able to take advantage from both labeled and unlabeled samples. Additionally, most of the times where SSL techniques can be deployed, only a small portion of samples in the data set is labeled. To deal with such situations in a straightforward fashion, in this paper we introduce a semi-supervised learning approach based on neuronal synchrony in a network of coupled integrate-and-fire neurons. For that, we represent the input data set as a graph and model each of its nodes by an integrate-and-fire neuron. Thereafter, we propagate the class labels from the seed samples to unlabeled samples through the graph by means of the emerging synchronization dynamics. Experimentations on synthetic and real data show that the introduced technique achieves good classification results regardless the feature space distribution or geometrical shape.

[1]  Ronald Rosenfeld,et al.  Semi-supervised learning with graphs , 2005 .

[2]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[3]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[4]  Fei Wang,et al.  Label Propagation through Linear Neighborhoods , 2006, IEEE Transactions on Knowledge and Data Engineering.

[5]  Avrim Blum,et al.  The Bottleneck , 2021, Monopsony Capitalism.

[6]  Ayhan Demiriz,et al.  Semi-Supervised Clustering Using Genetic Algorithms , 1999 .

[7]  D. Wang,et al.  The time dimension for scene analysis , 2005, IEEE Transactions on Neural Networks.

[8]  Anderson Rocha,et al.  Progressive randomization: Seeing the unseen , 2010, Comput. Vis. Image Underst..

[9]  DeLiang Wang,et al.  Synchrony and Desynchrony in Integrate-and-Fire Oscillators , 1999, Neural Computation.

[10]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[11]  S. Strogatz,et al.  Synchronization of pulse-coupled biological oscillators , 1990 .

[12]  DeLiang Wang,et al.  Object selection based on oscillatory correlation , 1999, Neural Networks.

[13]  Anderson Rocha,et al.  Multi-class from Binary - Divide to conquer , 2009, VISAPP.

[14]  Zhi-Hua Zhou,et al.  Semisupervised Regression with Cotraining-Style Algorithms , 2007, IEEE Transactions on Knowledge and Data Engineering.

[15]  J J Hopfield,et al.  Rapid local synchronization of action potentials: toward computation with coupled integrate-and-fire neurons. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[16]  Thorsten Joachims,et al.  Transductive Learning via Spectral Graph Partitioning , 2003, ICML.

[17]  Eugene M. Izhikevich,et al.  Which model to use for cortical spiking neurons? , 2004, IEEE Transactions on Neural Networks.

[18]  Jürgen Kurths,et al.  Synchronization: Phase locking and frequency entrainment , 2001 .

[19]  DeLiang Wang,et al.  Emergent synchrony in locally coupled neural oscillators , 1995, IEEE Trans. Neural Networks.

[20]  L. Rosasco,et al.  Manifold Regularization , 2007 .

[21]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[22]  Pawan Sinha,et al.  Face Recognition by Humans: Nineteen Results All Computer Vision Researchers Should Know About , 2006, Proceedings of the IEEE.

[23]  Roseli A. Francelin Romero,et al.  An oscillatory correlation model of object-based attention , 2009, 2009 International Joint Conference on Neural Networks.

[24]  Y. Kuramoto.  Collective synchronization of pulse-coupled oscillators and excitable units , 1991 .

[25]  Naonori Ueda,et al.  A Hybrid Generative/Discriminative Approach to Semi-Supervised Classifier Design , 2005, AAAI.

[26]  Zhi-Hua Zhou,et al.  Tri-training: exploiting unlabeled data using three classifiers , 2005, IEEE Transactions on Knowledge and Data Engineering.

[27]  Jürgen Kurths,et al.  Synchronization - A Universal Concept in Nonlinear Sciences , 2001, Cambridge Nonlinear Science Series.

[28]  Zoubin Ghahramani,et al.  Combining active learning and semi-supervised learning using Gaussian fields and harmonic functions , 2003, ICML 2003.

[29]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[30]  DeLiang Wang,et al.  Image Segmentation Based on Oscillatory Correlation , 1997, Neural Computation.

[31]  Deliang Wang,et al.  Global competition and local cooperation in a network of neural oscillators , 1995 .

[32]  Guy J. Brown,et al.  A computational model of auditory selective attention , 2004, IEEE Transactions on Neural Networks.

[33]  Alex Arenas,et al.  Mechanisms of synchronization and pattern formation in a lattice of pulse-coupled oscillators , 1998 .

[34]  Mikhail Belkin,et al.  Regularization and Semi-supervised Learning on Large Graphs , 2004, COLT.

[35]  Hichem Frigui,et al.  Self-Organization of Pulse-Coupled Oscillators with Application to Clustering , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[36]  Jacques Wainer,et al.  Automatic fruit and vegetable classification from images , 2010 .

[37]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

[38]  Guy J. Brown,et al.  Separation of speech from interfering sounds based on oscillatory correlation , 1999, IEEE Trans. Neural Networks.

[39]  Tom Michael Mitchell,et al.  The Role of Unlabeled Data in Supervised Learning , 2004 .

[40]  Avrim Blum,et al.  Learning from Labeled and Unlabeled Data using Graph Mincuts , 2001, ICML.

[41]  Arenas,et al.  Synchronization in a lattice model of pulse-coupled oscillators. , 1995, Physical review letters.

[42]  Ricardo da Silva Torres,et al.  Content-Based Image Retrieval: Theory and Applications , 2006, RITA.

[43]  Stefan C. Kremer,et al.  Clustering unlabeled data with SOMs improves classification of labeled real-world data , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[44]  Marc Timme,et al.  Speed of synchronization in complex networks of neural oscillators: analytic results based on Random Matrix Theory. , 2005, Chaos.

[45]  Steven Abney,et al.  Semisupervised Learning for Computational Linguistics , 2007 .