The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.
TY - CONF AU - Sun, Y.P. ED - Yamazaki, Yoshishige ED - Raubenheimer, Tor ED - McCausey, Amy ED - Schaa, Volker RW TI - Transfer Matrix Classification with Artificial Neural Network J2 - Proc. of NAPAC2019, Lansing, MI, USA, 01-06 September 2019 CY - Lansing, MI, USA T2 - North American Particle Accelerator Conference T3 - 4 LA - english AB - Standard neural network algorithms are developed for classification and regression applications. In this paper, the details of the neural network algorithms are presented, together with several applications. Artificial neural network is trained to classify multi-class transfer matrix of different types of particle accelerator components. It is shown that with a fully-connected feedforward neural network, it is possible to get high accuracy of 99% on training data, validation data and test data. PB - JACoW Publishing CP - Geneva, Switzerland SP - 898 EP - 900 KW - network KW - quadrupole KW - dipole KW - framework KW - software DA - 2019/10 PY - 2019 SN - 2673-7000 SN - 978-3-95450-223-3 DO - doi:10.18429/JACoW-NAPAC2019-WEPLE07 UR - http://jacow.org/napac2019/papers/weple07.pdf ER -