Seite - 189 - in Adaptive and Intelligent Temperature Control of Microwave Heating Systems with Multiple Sources

Bibliography [Bar89] Horace B Barlow. Unsupervised learning. Neural computation, 1(3):295–311,1989. [Bar94] Andrew G Barto. Reinforcement learning control. CurrentOpinion inNeurobiology, 4(6):888–893,1994. [Bar98] Andrew G Barto. Reinforcement learning: An intro- duction. MITpress,1998. [Bar01] Michael Barr. Pulse width modulation. Embedded SystemsProgramming, 14(10):103–104,2001. [Bat92] Roberto Battiti. First-and second-order methods for learning: between steepest descent and Newton’s method. Neural computation, 4(2):141–166,1992. [BBBB95] Dimitri P Bertsekas, Dimitri P Bertsekas, Dimitri P Bertsekas, and Dimitri P Bertsekas. Dynamic pro- gramming and optimal control, volume 1. Athena Sci- entificBelmont,MA,1995. [BBG+03] SW Berg, D Bromberek, J Gagliano, AE Grelick, G Goeppner, A Nassiri, and T Smith. Rebuilding WR-340 and WR-284 waveguide switches to meet higher power at the advanced photon source. In Particle Accelerator Conference, 2003. PAC 2003. Pro- ceedings of the, volume 2, pages 1416–1418. IEEE, 2003. [BC06] Bruno Bouzy and Guillaume Chaslot. Monte-Carlo Go reinforcement learning experiments. In Compu- tational Intelligence and Games, 2006 IEEE Symposium on,pages187–194. IEEE,2006. [BDVW97] S Bradshaw, S Delport, and E Van Wyk. Qualita- tive measurement of heating uniformity in a multi- mode microwave cavity. Journal of microwave power andelectromagnetic energy, 32(2):88–95,1997. [Bel57] Richard Bellman. A Markovian decision process. Technical report,DTICDocument,1957. [BG97] ZviBogerandHugoGuterman. Knowledgeextrac- tion from artificial neural network models. In Sys- 189