Learning in Intelligent Embedded Systems

Information processing capabilities of embedded systems presently lack the robustness and rich complexity found in biological systems. Endowing artificial systems with the ability to adapt to changing conditions requires algorithms that can rapidly learn from examples. We demonstrate the application of one such learning algorithm on an inexpensive robot constructed to perform simple sensorimotor tasks. The robot learns to track a particular object by discovering the salient visual and auditory cues unique to that object. The system uses a convolutional neural network to combine color, luminance, motion, and auditory information. The weights of the networks are adjusted using feedback from a teacher to reflect the reliability of the various input channels in the surrounding environment. We also discuss how unsupervised learning can discover features in data without external interaction. An unsupervised algorithm based upon nonnegative matrix factorization is able to automatically learn the different parts of objects. Such a parts-based representation of data is crucial for robust object recognition.

[1]  A. L. I︠A︡rbus.  Eye Movements and Vision , 1967 .

[2]  A. L. Yarbus,et al.  Eye Movements and Vision , 1967, Springer US.

[3]  William H. Richardson,et al.  Bayesian-Based Iterative Method of Image Restoration , 1972 .

[4]  L. Lucy.  An iterative technique for the rectification of observed distributions , 1974 .

[5]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[6]  S. Palmer.  Hierarchical structure in perceptual representation , 1977, Cognitive Psychology.

[7]  Michael McGill,et al.  Introduction to Modern Information Retrieval , 1983 .

[8]  I. Biederman.  Recognition-by-components: a theory of human image understanding. , 1987, Psychological review.

[9]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[10]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[11]  Q. Summerfield.  Book Review: Auditory Scene Analysis: The Perceptual Organization of Sound , 1992 .

[12]  M Konishi,et al.  Listening with two ears. , 1993, Scientific American.

[13]  Christof Koch,et al.  An Analog VLSI Saccadic Eye Movement System , 1993, NIPS.

[14]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[15]  John C. Platt,et al.  A Convolutional Neural Network Hand Tracker , 1994, NIPS.

[16]  Alexandros Eleftheriadis,et al.  Automatic face location detection and tracking for model-assisted coding of video teleconferencing sequences at low bit-rates , 1995, Signal Process. Image Commun..

[17]  Geoffrey E. Hinton,et al.  The "wake-sleep" algorithm for unsupervised neural networks. , 1995, Science.

[18]  Rajesh P. N. Rao,et al.  Modeling Saccadic Targeting in Visual Search , 1995, NIPS.

[19]  Takeo Kanade,et al.  Human Face Detection in Visual Scenes , 1995, NIPS.

[20]  Alexander H. Waibel,et al.  A real-time face tracker , 1996, Proceedings Third IEEE Workshop on Applications of Computer Vision. WACV'96.

[21]  H. Sebastian Seung,et al.  Unsupervised Learning by Convex and Conic Coding , 1996, NIPS.

[22]  Hans Peter Graf,et al.  Robust face feature analysis for automatic speechreading and character animation , 1996, Proceedings of the Second International Conference on Automatic Face and Gesture Recognition.

[23]  David J. Field,et al.  Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[24]  Trevor Darrell,et al.  A novel environment for situated vision and behavior , 1994 .

[25]  Susan T. Dumais,et al.  The latent semantic analysis theory of knowledge , 1997 .

[26]  Fernando Pereira,et al.  Aggregate and mixed-order Markov models for statistical language processing , 1997, EMNLP.

[27]  Tomaso A. Poggio,et al.  Example-Based Learning for View-Based Human Face Detection , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[28]  Peter Földiák,et al.  SPARSE CODING IN THE PRIMATE CORTEX , 2002 .