bionic architecture by using deep learning algorithms

The main reason of bionic architecture is the designs of curved forms reminiscent of structures in biology and fractal mathematics. in the past decades, the methods that are much more economical to achieve reasonable accuracy are always required. in recent years, there has been a growing interest in using artificial neural networks (anns), a computing technique that works in a way similar to that of biological nervous systems. many researchers used ann to study a beamusing multilayer perceptron (mlp) ann. furthermore, another application of ann is to evaluation of the failure probability and safety levels of structural systems. bakhshi and vazirizade used a radial network in order to predict the stiffness of the each member in a frame according to its response to a record. in fact, they showed ann can provide a mapping from themaximum story drifts to columns stiffness.