Deep Machine Learning-A New Frontier in Artificial Intelligence Research
Deep Machine Learning-A New Frontier in Artificial Intelligence Research
复制标题
DOI：
10.1109/mci.2010.938364
复制
发表时间：
2010-11-01
影响因子：
9
通讯作者：
Karnowski, Thomas P.
中科院分区：
文献类型：
--
作者：
Arel, Itamar;Rose, Derek C.;Karnowski, Thomas P.
本文对过去十年提出的主流深度学习方法和研究方向进行了综述。必须强调的是，每种方法都有各自的优点和“缺点，这取决于使用它的应用程序和环境”。因此，本文对深度机器学习领域的现状进行了总结，并对其可能的发展前景进行了展望。卷积神经网络(CNN)和深度信念网络(DBN)(及其各自的变体)之所以受到关注，主要是因为它们在深度学习领域已经建立了很好的基础，并显示出巨大的未来工作前景。
This article provides an overview of the mainstream deep learning approaches and research directions proposed over the past decade. It is important to emphasize that each approach has strengths and "weaknesses, depending on the application and context in "which it is being used. Thus, this article presents a summary on the current state of the deep machine learning field and some perspective into how it may evolve. Convolutional Neural Networks (CNNs) and Deep Belief Networks (DBNs) (and their respective variations) are focused on primarily because they are well established in the deep learning field and show great promise for future work.