Abstract | ||
---|---|---|
We propose to learn a curriculum or a syllabus for supervised learning with deep neural networks. Specifically, we learn weights for each sample in training by an attached neural network, called ScreenerNet, to the original network and jointly train them in an end-to-end fashion. We show the networks augmented with our ScreenerNet achieve early convergence with better accuracy than the state-of-the-art rule-based curricular learning methods in extensive experiments using three popular vision datasets including MNIST, CIFAR10 and Pascal VOC2012, and a Cartpole task using Deep Q-learning. |
Year | Venue | Field |
---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Convergence (routing),MNIST database,Syllabus,Computer science,Supervised learning,Curriculum,Artificial intelligence,Artificial neural network,Deep neural networks |
DocType | Volume | Citations |
Journal | abs/1801.00904 | 0 |
PageRank | References | Authors |
0.34 | 9 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tae-Hoon Kim | 1 | 1 | 1.36 |
Jonghyun Choi | 2 | 272 | 14.29 |