Neural networks are machine learning systems that perform
computation across a collection of interconnected processing
units, mimicking systems of neurons in a mammalian brain.
The weights of the connections between processing units
determine the overall behavior of the network. These weights
are adaptively tuned to data through a process of "learning".
The trained networks that result after learning are capable
of accurately representing functional dependencies in data.
My recent work in neural networks has involved the development
of network architectures that allow faster learning without a
loss of predictive performance. I have also done work on visualization
of neural networks, and on metrics that allow quantifying the
degree of organization and symmetry in neuronal systems.
Publications on neural networks (asterisks * denote student co-authors)
S. A. Alvarez, C. Ruiz, T. Kawato*, W. Kogel*.
"Neural Expert Networks for Faster Combined Collaborative and Content-Based
Journal of Computational Methods in Sciences and Engineering,
vol 11, no 4, Sept. 2011, 161-172
Alvarez, S.A., Ruiz, C., and Kawato*, T.
"More Efficient Mining over Heterogeneous Data using Neural Expert Networks",
in Multimedia Data Mining and Knowledge Discovery
(V.A. Petrushin and L. Khan, eds.),
Alvarez, S.A., Kawato*, T., Ruiz, C.,
"Mining over Loosely Coupled Data Sources using Neural Experts",
Fourth International Workshop on Multimedia Data Mining (MDM/KDD 2003),
in conjunction with the Ninth ACM SIGKDD International Conference on
Knowledge Discovery and Data Mining (KDD2003),
Washington, DC, Aug. 2003
Streeter*, M.J., Ward, M.O., Alvarez, S.A.,
``N2VIS -- An Interactive Visualization Tool for Neural Networks'',
Visual Data Exploration and Analysis VIII, Proc. SPIE Vol. 4302,
San Jose, CA, Jan. 2001; also see
Technical Report WPI-CS-TR-00-11, Department of Computer Science,
Worcester Polytechnic Institute, March 2000
- Alvarez, S.A., Levitan, S.L., Reggia, J.A.,
"Metrics for Cortical Map Organization and Asymmetry",
Bulletin of Mathematical Biology, vol. 60 (1998), 27-47