NW Computational Intelligence Lab
Portland State University
[background graphic]
Home  | People  | Publications  | Software  | Links  | Animations
 |
[background graphic]

Faculty

Students

Past Students

Roberto Santiago

Roberto Santiago

Laboratory Manager, Research Assistant

PhD Student, System Science, Portland State University
BS, Mathematics, Univeristy of Maryland, College Park (2001)

Email: robes at pdx dot edu
Phone: (503) 725-4997


Research Interests:

My primary research interests span the spectrum of disciplines ranging from neuroscience to neuroengineering to philosophy of mind. Originally fascinated by the promises of artificial intelligence, I have focused my research efforts on understanding the aspects of intelligence that seem difficult to reproduce and understand. In particular, the ability for humans (as well as many animals) to learn new tasks and then adapt and reuse this knowledge in novel situations seems elusive to machine intelligence currently. Toward this end I am working within the field of reinforcement learning to improve adaptive critic algorithms (a.k.a. neurodynamic programming and approximate dynamic programming). The goal is to have a single intelligent machine learn several tasks and using that knowledge cope with novel situations. A major source of inspiration has been the study of neurobiological systems from the cellular to systemic level. In particular, I am looking to understand how information is processed within the brain. Among the most productive aspects of this research is the exploration of neuronal spike trains. These spike trains seem to form the foundation of very flexible information processing system. As such, spiking neural network models are of great interest as are models for neuronal membrane processing. Lastly, the philosophy of mind has always intrigued me with its characterization of intelligence. In particular Fodor's systematicity arguments seem like one of the few proper characterizations of mind. To that end, I have been working to translate some of these philosophical analysis into systemic concepts that can be more braodly used to guide my research in computational intelligence.


Professional Affiliations:

  • American Association for the Advancement of Science
  • International Neural Network Society
  • Institute of Electrical and Electronics Engineering
  • American Association of Artificial Intelligence

Publications

  • Santiago, R. A. & G. G. Lendaris (2004). "Context Discerning Multifunction Networks: Reformulating fixed weight neural networks." Proceedings of the International Joint Conference on Neural Networks (IJCNN2004), Budapest, Hungary, IEEE Press.

  • Lendaris, G.G., R.A. Santiago, J. McCarthy & M.S. Carroll (2003), "Controller Design via Adaptive Critic and Model Reference Methods," Proceedings of International Joint Conference on Neural Networks'03 (IJCNN' 2003),Portland, OR, paper #775, IEEE Press, July.HTML Abstract, pdf paper

  • Santiago, R.A., J. McNames, K.J. Burchiel & G.G. Lendaris (2003), "An Automated Method for Neuronal Spike Source Identification," Proceedings of International Joint Conference on Neural Networks'R03 (IJCNN' 2003),Portland, OR, paper #781, IEEE Press, July. HTML Abstract, pdf paper

  • Santiago, R. A., J. McNames, et al. (2003). "Developments in understanding neuronal spike trains and functional specialization in brain regions." Neural Networks 16(5-6): 601-607.

  • Shannon, T.T., R.A. Santiago & G.G. Lendaris (2003), "Accelerated Critic Learning In Approximate Dynamic Programming via Value Templates and Perceptual Learning," Proceedings of International Joint Conference on Neural Networks'R032 (IJCNN' 2003), paper #775, Portland, OR, IEEE Press, July.HTML Abstract, pdf paper

  • Lendaris, G.G., R.A. Santiago & M.S. Carroll (2002), "Proposed Framework for Applying Adaptive Critics in Real-Time Realm," Proceedings of International Conference on Neural Networks'R02 (IJCNN' 2002), Hawaii, May. HTML Abstract, pdf paper

  • Prokhorov, D., R. A. Santiago & D.Wunsch (1995). "Adaptive critic designs: A case study for neurocontrol." Neural Networks 8(9): 1367-1372.

  • Santiago, R. A. and P. J. Werbos (1994). "New progress towards truly brain-like control." Proceedings of the World Congress on Neural Networks (WCNN1994), San Diego, CA, INNS Press.

  • Werbos, P.J. & R.A. Santiago (1993), "Neurocontrol," Above Threshold (International Neural Network Society Newsletter) 2(2)

Last modified Sunday, 4 June 2006