Poster
Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
Haw-Shiuan Chang · Erik Learned-Miller · Andrew McCallum
Pacific Ballroom #228
Keywords: [ Efficient Training Methods ] [ Optimization for Deep Networks ] [ Natural Language Processing ] [ Classification ] [ Computer Vision ] [ Supervised Deep Networks ] [ Active Learning ]
Self-paced learning and hard example mining re-weight training instances to improve learning accuracy. This paper presents two improved alternatives based on lightweight estimates of sample uncertainty in stochastic gradient descent (SGD): the variance in predicted probability of the correct class across iterations of mini-batch SGD, and the proximity of the correct class probability to the decision threshold. Extensive experimental results on six datasets show that our methods reliably improve accuracy in various network architectures, including additional gains on top of other popular training techniques, such as residual learning, momentum, ADAM, batch normalization, dropout, and distillation.
Live content is unavailable. Log in and register to view live content