arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.08259cs.LGcs.CVstat.ML
收藏

基于置信度的深度神经网络自适应包围预测

Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence Level

IBM Research - Tokyo(IBM东京研究院)

Hiroshi Inoue

摘要:

集成多个预测是用于提高各种机器学习任务的准确性的广泛使用的技术。集成的一个明显的缺点是它在推理过程中的执行成本较高。在本文中,我们首先描述了我们对预测概率与当前深度神经网络集成效果之间关系的见解;即使有不可忽略的错误预测输入,集成也无助于预测概率很高的输入的错误预测。这一发现促使我们开发一种自适应控制集成的方法。如果对输入的预测达到足够高的概率,即,softmax函数的输出,基于置信水平,我们停止对该输入进行集成,以避免浪费计算能力。我们通过使用各种数据集来评估自适应集成,并表明它显着降低了计算成本,同时使用预定义数量的局部预测实现了与静态集成相似的精度。我们还表明,我们的统计严格的置信水平为基础的提前退出条件,减少了任务相关的阈值调整的负担更好地与天真的提前退出的基础上预先定义的阈值相比,除了产生更好的精度与相同的成本。

英文摘要:

Ensembling multiple predictions is a widely used technique for improving the accuracy of various machine learning tasks. One obvious drawback of ensembling is its higher execution cost during inference. In this paper, we first describe our insights on the relationship between the probability of prediction and the effect of ensembling with current deep neural networks; ensembling does not help mispredictions for inputs predicted with a high probability even when there is a non-negligible number of mispredicted inputs. This finding motivated us to develop a way to adaptively control the ensembling. If the prediction for an input reaches a high enough probability, i.e., the output from the softmax function, on the basis of the confidence level, we stop ensembling for this input to avoid wasting computation power. We evaluated the adaptive ensembling by using various datasets and showed that it reduces the computation cost significantly while achieving accuracy similar to that of static ensembling using a pre-defined number of local predictions. We also show that our statistically rigorous confidence-level-based early-exit condition reduces the burden of task-dependent threshold tuning better compared with naive early exit based on a pre-defined threshold in addition to yielding a better accuracy with the same cost.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑