From ADP to the brain: Foundations, roadmap, challenges and research priorities

This paper defines and discusses "Mouse Level Computational Intelligence" (MCLI) as a grand challenge for the coming century. It provides a specific roadmap to reach that target, citing relevant work and review papers and discussing the relation to funding priorities in two NSF funding activities. The ongoing Energy, Power and Adaptive Systems program (EPAS) and the recent initiative in Cognitive Optimization and Prediction (COPN). It elaborates on the first step, "vector intelligence," a challenge in the development of universal learning systems, which itself will require considerable new research to attain. This in turn is a crucial prerequisite to true functional understanding of how mammal brains achieve such general learning capabilities.

[1]  Amir F. Atiya,et al.  A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition , 2011, Expert Syst. Appl..

[2]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[3]  Robert Kozma,et al.  Advances in Neuromorphic Memristor Science and Applications , 2012, Springer Series in Cognitive and Neural Systems.

[4]  Ganesh K. Venayagamoorthy,et al.  Function Approximations with Multilayer Perceptrons and Simultaneous Recurrent Metworks , 2004 .

[5]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[6]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part I , 1964, Inf. Control..

[7]  Paul J. Werbos,et al.  Neural networks and the experience and cultivation of mind , 2012, Neural Networks.

[8]  A. Barron.  Approximation and Estimation Bounds for Artificial Neural Networks , 1991, COLT '91.

[9]  Paul J. Werbos,et al.  Stable adaptive control using new critic designs , 1998, Other Conferences.

[10]  Hans-Georg Zimmermann,et al.  Recurrent Neural Networks are Universal approximators , 2007, Int. J. Neural Syst..

[11]  Danil V. Prokhorov,et al.  Enhanced Multi-Stream Kalman Filter Training for Recurrent Networks , 1998 .

[12]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part II , 1964, Inf. Control..

[13]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[14]  Paul J. Werbos,et al.  2009 Special Issue: Intelligence in the brain: A theory of how it works and how to build it , 2009 .

[15]  Frank L. Lewis,et al.  Reinforcement Learning and Approximate Dynamic Programming for Feedback Control , 2012 .

[16]  Paul J. Werbos,et al.  Fuzziness, Probability, Uncertainty and the Foundations of Knowledge , 2013, On Fuzziness.

[17]  Paul J. Werbos,et al.  Computational Intelligence for the Smart Grid-History, Challenges, and Opportunities , 2011, IEEE Computational Intelligence Magazine.