Robustness of hardware-oriented restricted Boltzmann machines in deep belief networks for reliable processing
Kodai Ueyoshi, Takao Marukame, Tetsuya Asai, Masato Motomura, Alexandre Schmid · Nonlinear Theory and Its Applications IEICE · 2016
Remarkable hardware robustness of deep learning is revealed from an error-injection analysis performed using a custom hardware model implementing parallelized restricted Boltzmann machines (RBMs). RBMs used in deep belief networks (DBNs) demonstrate robustness against memory errors during and after learning. Fine-tuning has a significant impact on the recovery of accuracy under the presence of static errors that may modify structural data of RBMs. The proposed hardware networks with fine-graded memory distribution are observed to tolerate memory errors, thereby resulting in a reliable deep learning hardware platform, potentially suitable to safety-critical embedded applications.