One of the author proposed a learning algorithm, called“FTL-algo”, which make 3-layered perceptrons multipleweight-and-neuron-fault tolerant, developed its CUDA Ccode, and gave the result using GPU. The FTL-algo is anordinary back propagation algorithm with some modification.However, the FTL-algo using Deep Learning Frameworkshave not been found.The purpose of this study is to evaluate in time andaccuracy of learning when the FTL-algo calculation is doneusing Deep Learning Frameworks to compare with previousresult.
展开▼