Abstract
This paper proposes a new propagator for a set of Neuron Constraints representing a two-layer network. Neuron Constraints are employed in the context of the Empirical Model Learning technique, that enables optimal decision making over complex systems, beyond the reach of most conventional optimization techniques. The approach is based on embedding a Machine Learning-extracted model into a combinatorial model. Specifically, a Neural Network can be embedded in a Constraint Model by simply encoding each neuron as a Neuron Constraint, which is then propagated individually. The price for such simplicity is the lack of a global view of the network, which may lead to weak bounds. To overcome this issue, we propose a new network-level propagator based on a Lagrangian relaxation, that is solved with a subgradient algorithm. The approach is tested on a thermal-aware dispatching problem on multicore CPUs, and it leads to a massive reduction of the size of the search tree, which is only partially countered by an increased propagation time.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Bartolini, A., Lombardi, M., Milano, M., Benini, L.: Neuron Constraints to Model Complex Real-World Problems. In: Lee, J. (ed.) CP 2011. LNCS, vol. 6876, pp. 115–129. Springer, Heidelberg (2011)
Bartolini, A., Lombardi, M., Milano, M., Benini, L.: Optimization and Controlled Systems: A Case Study on Thermal Aware Workload Dispatching. Proc. of AAAI (2012)
Belew, R.K., McInerney, J., Schraudolph, N.N.: Evolving networks: Using the genetic algorithm with connectionist learning. In: Proc. of Second Conference on Artificial Life, pp. 511–547 (1991)
Chow, T.T., Zhang, G.Q., Lin, Z., Song, C.L.: Global optimization of absorption chiller system by genetic algorithm and neural network. Energy and Buildings 34(1), 103–109 (2002)
Frangioni, A., D’Antonio, G.: Deflected Conditional Approximate Subgradient Methods (Tech. Rep. TR-07-20). Technical report, University of Pisa (2007)
Ge, S.S., Hang, C.C., Lee, T.H., Zhang, T.: Stable adaptive neural network control. Springer Publishing Company, Incorporated (2010)
Glover, F., Kelly, J.P., Laguna, M.: New Advances for Wedding optimization and simulation. In: Proc. of WSC, pp. 255–260 (1999)
Gopalakrishnan, K., Ph, D., Asce, A.M.: Neural Network Swarm Intelligence Hybrid Nonlinear Optimization Algorithm for Pavement Moduli Back-Calculation. Journal of Transportation Engineering 136(6), 528–536 (2009)
Huang, W., Ghosh, S., Velusamy, S.: HotSpot: A compact thermal modeling methodology for early-stage VLSI design. IEEE Trans. on VLSI 14(5), 501–513 (2006)
Jayaseelan, R., Mitra, T.: A hybrid local-global approach for multi-core thermal management. In: Proc. of ICCAD, pp. 314–320. ACM Press, New York (2009)
Kiranyaz, S., Ince, T., Yildirim, A., Gabbouj, M.: Evolutionary artificial neural networks by multi-dimensional particle swarm optimization. Neural Networks 22(10), 1448–1462 (2009)
Ljung, L.: System identification. Wiley Online Library (1999)
Montana, D.J., Davis, L.: Training feedforward neural networks using genetic algorithms. In: Proc. of IJCAI, pp. 762–767 (1989)
Moore, J., Chase, J.S., Ranganathan, P.: Weatherman: Automated, Online and Predictive Thermal Mapping and Management for Data Centers. In: Proc. of IEEE ICAC, pp. 155–164. IEEE (2006)
Zhang, G., Patuwo, B.E., Hu, M.Y.: Forecasting with artificial neural networks: The state of the art. International Journal of Forecasting 14(1), 35–62 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lombardi, M., Gualandi, S. (2013). A New Propagator for Two-Layer Neural Networks in Empirical Model Learning. In: Schulte, C. (eds) Principles and Practice of Constraint Programming. CP 2013. Lecture Notes in Computer Science, vol 8124. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40627-0_35
Download citation
DOI: https://doi.org/10.1007/978-3-642-40627-0_35
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40626-3
Online ISBN: 978-3-642-40627-0
eBook Packages: Computer ScienceComputer Science (R0)