Connectionist Techniques For The Identification And Suppression Of Interfering Underlying Factors

We consider the difficult problem of identification of independent causes from a mixture of them when these causes interfere with one another in a particular manner: those considered are visual inputs to a neural network system which are created by independent underlying causes which may occlude each other. The prototypical problem in this area is a mixture of horizontal and vertical bars in which each horizontal bar interferes with the representation of each vertical bar and vice versa. Previous researchers have developed artificial neural networks which can identify the individual causes; we seek to go further in that we create artificial neural networks which identify all the horizontal bars from only such a mixture. This task is a necessary precursor to the development of the concept of "horizontal" or "vertical".

[1]  E. Oja,et al.  Principal component analysis by homogeneous neural networks, Part I : The weighted subspace criterion , 1992 .

[2]  Colin Fyfe,et al.  epsilon-insensitive Hebbian learning , 2002, Neurocomputing.

[3]  Colin Fyfe,et al.  A Neural Network for PCA and Beyond , 1997, Neural Processing Letters.

[4]  Ray H. White,et al.  Competitive hebbian learning: Algorithm and demonstrations , 1992, Neural Networks.

[5]  Jos Koetsier,et al.  Unsupervised neural networks for the identification of minimum overcomplete basis in visual data , 2002, Neurocomputing.

[6]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[7]  H. Sebastian Seung,et al.  The Rectified Gaussian Distribution , 1997, NIPS.

[8]  Colin Fyfe.  PCA Properties of Interneurons , 1993 .

[9]  Erkki Oja,et al.  Neural Networks, Principal Components, and Subspaces , 1989, Int. J. Neural Syst..

[10]  Lei Xu,et al.  Least mean square error reconstruction principle for self-organizing neural-nets , 1993, Neural Networks.

[11]  Geoffrey E. Hinton,et al.  Hierarchical Non-linear Factor Analysis and Topographic Maps , 1997, NIPS.

[12]  Aapo Hyvärinen,et al.  Complexity Pursuit: Separating Interesting Components from Time Series , 2001, Neural Computation.

[13]  Eric Saund,et al.  A Multiple Cause Mixture Model for Unsupervised Learning , 1995, Neural Computation.

[14]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[15]  D Charles,et al.  Modelling multiple-cause structure using rectification constraints. , 1998, Network.

[16]  Emilio Corchado,et al.  Rectified Gaussian distributions and the formation of local filters from video data , 2001, ESANN.

[17]  David J. Field,et al.  What Is the Goal of Sensory Coding? , 1994, Neural Computation.

[18]  C. Fyfe,et al.  Using noise to form a minimal overcomplete basis , 1999 .