arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.08569cs.LGcs.AI
收藏

使用基于Autoencoder的连续优化生成课程

Curriculum generation using Autoencoder based continuous optimization

Hike Ltd(Hike有限公司)

Dipankar Sarkar, Mukur Gupta

摘要:

在课程学习的研究中,通过优化训练数据的顺序,在任务上表现出更好的性能。最近的工作集中在使用复杂的强化学习技术来找到最佳的数据排序策略,以最大限度地提高给定网络的学习。在本文中,我们提出了一种简单而有效的技术,基于自动编码过程训练的连续优化。我们称这种新方法为训练序列优化(TSO)。通过通常的编码器-解码器设置,我们尝试学习训练策略的潜在空间连续表示,并在连续表示上使用预测器网络来预测固定网络架构上策略的准确性。性能预测器和编码器使我们能够执行基于梯度的优化,逐步走向潜在的更好的精度排序的训练数据的潜在空间表示。使用CIFAR-100和CIFAR-10数据集,我们生成的最佳课程策略比随机策略的经验增益为2AP,并且比现有的最先进的CL算法有更好的提升。

英文摘要:

Research in Curriculum Learning has shown better performance on the task by optimizing the sequence of the training data. Recent works have focused on using complex reinforcement learning techniques to find the optimal data ordering strategy to maximize learning for a given network. In this paper, we present a simple yet efficient technique based on continuous optimization trained with auto-encoding procedure. We call this new approach Training Sequence Optimization (TSO). With a usual encoder-decoder setup we try to learn the latent space continuous representation of the training strategy and a predictor network is used on the continuous representation to predict the accuracy of the strategy on the fixed network architecture. The performance predictor and encoder enable us to perform gradient-based optimization by gradually moving towards the latent space representation of training data ordering with potentially better accuracy. We show an empirical gain of 2AP with our generated optimal curriculum strategy over the random strategy using the CIFAR-100 and CIFAR-10 datasets and have better boosts than the existing state-of-the-art CL algorithms.

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。

↑