@inbook{1a26ea7d82e54824b4cba4c698eae408,
title = "Tri-self-taught learning of artificial neural networks",
abstract = "We present a conceptually simple and general framework for self-taught learning, and this method can modify weights of neural networks when making prediction on samples according to the previous knowledge. The method called Tri-STNN. Based on Tri-training, it adds a Judge Network to make a higher accuracy of prediction. Tri-STNN is simple to be trained and the training datasets for Judge Network is easy to obtain. Moreover, Tri-STNN is capable of lots of tasks. We test Tri-STNN on the datasets of CIFAR-10, and the result shows that Tri-STNN can constantly keep self-taught learning and improve the generalization ability for new samples.",
keywords = "Artificial neural networks, Judge network, Lifelong- learning, Self-taught learning",
author = "Feng Liu and Shuling Dai",
note = "Publisher Copyright: {\textcopyright} 2019, Springer Nature Singapore Pte Ltd.",
year = "2019",
doi = "10.1007/978-981-13-2291-4\_78",
language = "英语",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "807--814",
booktitle = "Lecture Notes in Electrical Engineering",
address = "德国",
}