Learning Deep Architectures for AI
Learning Deep Architectures for AI
复制标题
DOI：
10.1561/2200000006
复制
发表时间：
2009-01-01
影响因子：
32.8
通讯作者：
Bengio, Yoshua
中科院分区：
文献类型：
--
作者：
Bengio, Yoshua
理论结果表明，为了学习可以表示高级抽象的复杂函数（例如，在视觉、语言和其他AI级任务中），可能需要更深的架构。深度架构由多层非线性运算组成，例如在具有许多隐藏层的神经网络中，或者在重复使用许多子公式的复杂命题公式中。搜索深度架构的参数空间是一项艰巨的任务，但是最近已经提出了诸如深度信念网络的学习算法来解决这个问题，并取得了显着的成功，在某些领域击败了最先进的技术。这本专著讨论了深度架构学习算法的动机和原理，特别是那些利用单层模型（如受限玻尔兹曼机）的无监督学习作为构建块的算法，用于构建更深层次的模型，如深度信念网络。
Theoretical results suggest that in order to learn the kind of complicated functions that can represent high-level abstractions (e.g., in vision, language, and other AI-level tasks), one may need deep architectures. Deep architectures are composed of multiple levels of non-linear operations, such as in neural nets with many hidden layers or in complicated propositional formulae re-using many sub-formulae. Searching the parameter space of deep architectures is a difficult task, but learning algorithms such as those for Deep Belief Networks have recently been proposed to tackle this problem with notable success, beating the stateof- the-art in certain areas. This monograph discusses the motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer models such as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks.