en Applications Applications پژوهشي Research <span style="font-size:11.5pt"><span new="" roman="" style="font-family:" times=""><span style="layout-grid-mode:line">This paper employs neural network models to assess the seismic confidence levels at various performance levels, as well as the seismic collapse capacity of steel moment-resisting frame structures. Two types of shallow neural network models including back-propagation (BP) and radial basis (RB) models are utilized to evaluate the seismic responses. Both neural network models consist of a single hidden layer with a different number of neurons. The prediction accuracy of the trained neural network models is compared using two illustrative examples of 6- and 12-story steel moment-resisting frames. The obtained numerical results indicate that the BP model outperforms the RB model in predicting seismic responses.</span></span></span> seismic life cycle cost, performance-based design, nonlinear response history analysis, steel moment resisting frame 629 645 http://ijoce.iust.ac.ir/browse.php?a_code=A-10-6463-13&slc_lang=en&sid=1 A. Hassan Radhi Alhilali 180031947532846002553 180031947532846002553 No Department of Civil Engineering, Urmia University, Urmia, Iran S. Gholizadeh s.gholizadeh@urmia.ac.ir 180031947532846002554 180031947532846002554 Yes Department of Civil Engineering, Urmia University, Urmia, Iran S. Tariverdilo 180031947532846002555 180031947532846002555 No Department of Civil Engineering, Urmia University, Urmia, Iran