- 期刊
- OpenAccess
Automated Architecture Selection for Radial Basis Function Neural Networks
並列摘要
A new model selection algorithm is established to determine the best number of hidden neurons for radial basis function neural networks. We used a Bayesian information-based criterion to select the best number of hidden neurons. The new algorithm grows the number of hidden neurons while the Bayesian information-based criterion is used for improvement. The optimal parameter values of a current neural network are used in the subsequent architecture. The computational results are compared with the trial-and-error approach through publicly available data sets. It is found that the new algorithm is suitable to improve the performance of the neural networks automatically. The root mean square error function is used to measure out-of-sample performance.
延伸閱讀
- Shih, C. Y. (2011). An Improved Radial Basis Function Neural Network and Its Applications [doctoral dissertation, Yuan Ze University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0009-2801201414583086
- Lee, F. Y. (2021). Function approximation with neural network - A direct construction [master's thesis, National Tsing Hua University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0016-2412202116165779
- 陳慶全（2006）。Implementation and Application of Improved Toroidal Artificial Neural Networks Structure〔碩士論文，國立臺北科技大學〕。華藝線上圖書館。https://www.airitilibrary.com/Article/Detail?DocID=U0006-2607200614545200
- 蘇信華（2001）。Application of Artificial Neural Network to Structural Modal Analysis〔碩士論文，中原大學〕。華藝線上圖書館。https://doi.org/10.6840/cycu200100442
- Li, H. T. (2016). Human Action Recognition Using Geometric Parameter Features and a Radial Basis Function Neural Network. 網際網路技術學刊, 17(2), 255-261. https://doi.org/10.6138/JIT.2016.17.2.20160225