Application of the BP Neural Network Based on Conjugate Gradient Optimization Algorithm in the Identi cation of High Energy Particles and Other Fields
doi: 10.11804/NuclPhysRev.31.03.401
- Received Date: 1900-01-01
- Rev Recd Date: 1900-01-01
- Publish Date: 2014-09-20
-
Key words:
- BP neural network /
- conjugate gradient /
- step optimization /
- particle identification
Abstract: Artificial neural network methods have been introduced in high energy physics experiments and have been widely applied to the identification of the quark-gluon injection, electronic hadron discrimination,top quark, and the Higgs particle searching and so on. This paper introduces a modified conjugate gradient optimization algorithm, which is applied to the identification of high-energy particles. In the application, the algorithm can obtain optimal step size in the search direction for minimizing the objective function, and can overcome the local vibration problem, so that the fast convergence of the objective function is obtained and the stability of the algorithm is improved. The analysis of experimental data shows that our new BP neural network algorithm can effectively improve the identification of particles in high energy physics.
Citation: | WANG Shuwang, LU Yonggang, CHEN Xurong. Application of the BP Neural Network Based on Conjugate Gradient Optimization Algorithm in the Identi cation of High Energy Particles and Other Fields[J]. Nuclear Physics Review, 2014, 31(3): 401-406. doi: 10.11804/NuclPhysRev.31.03.401 |