Multi-stream Exploratory Projection Pursuit for the Formation of Complex Cells Similar to Visual Cortical Neurons

A multi-stream extension of Exploratory Projection Pursuit is proposed as a method for the formation of local, spatiotemporal, oriented filters similar to complex cells found in the visual cortex. This algorithm, which we call the Exploratory Correlation Analysis (ECA) network, is derived to maximise dependencies between separate, but related, data streams. By altering the functions on the outputs of the ECA network we can explore different forms of shared, higher order structure in multiple data streams.

[1]  Colin Fyfe,et al.  Noise to extract independent causes , 1999, ESANN.

[2]  Juha Karhunen,et al.  Representation and separation of signals using nonlinear PCA type learning , 1994, Neural Networks.

[3]  Colin Fyfe,et al.  Kernel exploratory projection pursuit , 2000, KES'2000. Fourth International Conference on Knowledge-Based Intelligent Engineering Systems and Allied Technologies. Proceedings (Cat. No.00TH8516).

[4]  Darryl Charles.  Challenges for Artificial Intelligence in Digital Games , 2003 .

[5]  Vilius Ivanauskas.  Conferences , 1979 .

[6]  Darryl Charles,et al.  The Past Present and Future of Artificial Neural Networks in Digital Games , 2004 .

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

[8]  Colin Fyfe,et al.  Learning Independent Causes of a Visual Data Set using the Rectified Gaussian Distribution , 1999, IIA/SOCO.

[9]  Kenji Okajima,et al.  An Infomax-based learning rule that generates cells similar to visual cortical neurons , 2001, Neural Networks.

[10]  Colin Fyfe,et al.  Kernel factor analysis with Varimax rotation , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[11]  Colin Fyfe,et al.  Neural networks which identify composite factors , 1999, ESANN.

[12]  Darryl Charles,et al.  AI: the Missing Link in Digital Game Interface Design? , 2004, ICEC.

[13]  D. Freedman,et al.  Asymptotics of Graphical Projection Pursuit , 1984 .

[14]  Darryl Charles,et al.  Intelligent Interfaces for Digital Games , 2004 .

[15]  Colin Fyfe,et al.  Exploratory Correlation Analysis , 2002, ESANN.

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

[17]  Darryl Charles,et al.  Dynamic Player Modelling: A Framework for Player-Centered Digital Games , 2004 .

[18]  Darryl Charles,et al.  Integrating Ideas About Invisible Playgrounds from Play Theory into Online Educational Digital Games , 2004, ICEC.

[19]  Colin Fyfe,et al.  Unsupervised models for processing visual data , 2001, ESANN.

[20]  Darryl Charles.  Enhancing gameplay: challenges for articifical intelligence in digital games , 2003, DiGRA Conference.

[21]  Darryl Charles,et al.  Statistically Based Learning Rules for Unsupervised Artificial Neural Networks and Low Level Visual Processing , 2002 .

[22]  Gerard Parr,et al.  Enabling Adaptive Multimedia over Wireless IP Networks , 2004 .

[23]  C. Fyfe,et al.  Rectified Gaussian distributions and the identification of multiple cause structure in data , 1999 .

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