Fault Tolerant Learning for Neural Networks: Survey, Framework and Future Work

While conventional learning theory focus on training a neural network to attain good generalization, fault tolerant learning aims at training a neural network to attain acceptable generalization even if network fault might appear in the future. This paper presents an extensive survey on the previous work done on fault tolerant learning. Those analytical works that have been reported in the literature and those algorithms that have been proposed to deal with weight noise or node fault will be elucidated. Furthermore, an objective function based framework for fault tolerant learning is proposed. Future work along the direction is presented.