When training neural networks for classification tasks with backpropagation, parameters are updated on every trial, even if the sample is classified correctly. In contrast, humans concentrate their learning effort on errors. Inspired by human learning, we introduce lazy learning, which only learns on incorrect samples. Lazy learning can be implemented in a few lines of code and requires no hyperparameter tuning. Lazy learning achieves state-of-the-art performance and is particularly suited when datasets are large. For instance, it reaches 99.2% test accuracy on Extended MNIST using a single-layer MLP, and does so 7.6x faster than a matched backprop network

翻译：在使用反向传播训练神经网络执行分类任务时，即使样本被正确分类，参数也会在每次试验中更新。相比之下，人类将学习精力集中在错误上。受人类学习的启发，我们引入了懒惰学习，该方法仅在错误样本上进行学习。懒惰学习仅需几行代码即可实现，且无需超参数调优。该方法达到了最先进的性能，尤其适用于大规模数据集。例如，使用单层多层感知机（MLP），该方法在扩展MNIST数据集上达到了99.2%的测试准确率，且速度比匹配的反向传播网络快7.6倍。