Neural networks leverage robust internal representations in order to generalise. Learning them is difficult, and often requires a large training set that covers the data distribution densely. We study a common setting where our task is not purely opaque. Indeed, very often we may have access to information about the underlying system (e.g. that observations must obey certain laws of physics) that any "tabula rasa" neural network would need to re-learn from scratch, penalising performance. We incorporate this information into a pre-trained reasoning module, and investigate its role in shaping the discovered representations in diverse self-supervised learning settings from pixels. Our approach paves the way for a new class of representation learning, grounded in algorithmic priors.
翻译:神经网络利用强大的内部代表来进行概括化。 学习它们是困难的, 通常需要一个包含数据密集分布的大型培训组。 我们研究我们的任务并非完全不透明的共同环境。 事实上, 我们常常有机会获得关于基础系统的信息( 比如观察必须遵从某些物理法则 ), 任何“ 塔布拉拉拉萨” 神经网络都需要从零开始重新学习, 惩罚性能。 我们将这些信息纳入一个预先培训的推理模块, 并调查其在从像素中构建不同自监督学习环境中的已发现代表的作用。 我们的方法为基于算法前科的新型代表学习铺平了道路 。