Learning from Mistakes -- A Framework for Neural Architecture Search
This work addresses the challenge of enhancing neural architecture search efficiency for machine learning practitioners, though it appears incremental as it adapts an existing human learning concept to a specific ML task.
The paper tackles the problem of improving neural architecture search by proposing a Learning From Mistakes (LFM) framework, which applies a human-inspired strategy of focusing on errors during revision, and reports strong experimental results on datasets like CIFAR-10, CIFAR-100, and ImageNet.
Learning from one's mistakes is an effective human learning technique where the learners focus more on the topics where mistakes were made, so as to deepen their understanding. In this paper, we investigate if this human learning strategy can be applied in machine learning. We propose a novel machine learning method called Learning From Mistakes (LFM), wherein the learner improves its ability to learn by focusing more on the mistakes during revision. We formulate LFM as a three-stage optimization problem: 1) learner learns; 2) learner re-learns focusing on the mistakes, and; 3) learner validates its learning. We develop an efficient algorithm to solve the LFM problem. We apply the LFM framework to neural architecture search on CIFAR-10, CIFAR-100, and Imagenet. Experimental results strongly demonstrate the effectiveness of our model.