论文信息 - Optimization of neural network weights and architectures for odor recognition using simulated annealing

Optimization of neural network weights and architectures for odor recognition using simulated annealing

Shows results of using simulated annealing for optimizing neural network architectures and weights. The algorithm generates networks with good generalization performance (mean classification error of 5.28%) and low complexity (mean number of connections of 11.68 out of 36) for an odor recognition task in an artificial nose.

[1] Krishna C. Persaud,et al. Arrays of broad specificity films for sensing volatile chemicals , 1997 .

[2] Stephan K. Chalup,et al. A study on hill climbing algorithms for neural network training , 1999, Proceedings of the 1999 Congress on Evolutionary Computation-CEC99 (Cat. No. 99TH8406).

[3] Xin Yao,et al. A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[4] C. D. Gelatt,et al. Optimization by Simulated Annealing , 1983, Science.

[5] Ibrahim Hassan Osman,et al. Metastrategy : simulated annealing and tabu search for combinatorial optimization problems , 1991 .

[6] Teresa B. Ludermir,et al. Classification of vintages of wine by artificial nose using time delay neural networks , 2001 .

[7] Xin Yao,et al. Evolving artificial neural networks , 1999, Proc. IEEE.

[8] Lutz Prechelt,et al. PROBEN 1 - a set of benchmarks and benchmarking rules for neural network training algorithms , 1994 .

[9] N. Metropolis,et al. Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[10] H. Eto,et al. Electronic noses-development and future prospects , 2022 .

[11] Michael Grüninger,et al. Introduction , 2002, CACM.

[12] Teresa Bernarda Ludermir,et al. Classification of Vintages of Wine by an Artificial Nose with Neural Networks , .

[13] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .