Curriculum learning is a training strategy that sorts the training examples by some measure of their difficulty and gradually exposes them to the learner to improve the network performance. Motivated by our insights from implicit curriculum ordering, we first introduce a simple curriculum learning strategy that uses statistical measures such as standard deviation and entropy values to score the difficulty of data points for real image classification tasks. We empirically show its improvements in performance with convolutional and fully-connected neural networks on multiple real image datasets. We also propose and study the performance of a dynamic curriculum learning algorithm. Our dynamic curriculum algorithm tries to reduce the distance between the network weight and an optimal weight at any training step by greedily sampling examples with gradients that are directed towards the optimal weight. Further, we use our algorithms to discuss why curriculum learning is helpful.
翻译:课程学习是一种培训战略,根据学习者的困难程度对培训实例进行分类,并逐渐让他们了解提高网络性能的学习情况。根据我们从隐性课程排序中获得的洞察力,我们首先引入一个简单的课程学习战略,使用标准偏差和增缩值等统计措施,对真实图像分类任务的数据点的难度进行评分。我们从经验上表明,在多个真实图像数据集上,与进化和完全连通的神经网络的性能有所改善。我们还提议并研究动态课程学习算法的性能。我们动态课程算法试图通过贪婪地用针对最佳重量的梯度抽样实例来缩短网络重量之间的距离和任何培训步骤的最佳重量。此外,我们用我们的算法来讨论课程学习为什么有用。