深度学习最新研究进展综述
首发时间:2014-08-15
摘要:深度学习作为机器学习领域的新兴技术,给人工智能及相关领域带来了生机与活力。首先,本文对深度学习的重要性、概念及特点进行了详细阐释,说明深度学习的价值及意义所在,然后对深度学习目前较成熟的两个典型模型:卷积神经网络、自动编码器进行了详细综述,并对其最新研究进展应用进行了概括,接着对深度学习中比较有潜力及实际意义的两个模型进行了介绍:多层核函数机(MKMs)及深度时空推理网模型(DeSTIN),为深度学习模型的发展方向注入新鲜力量,最后对深度学习模型的发展方向进行了总结。
For information in English, please click here
Study on deep learning
Abstract:Deep learning, which is an emerging technology of machine learning field, has brought vitality and vigor to artificial intelligence and related fields. Firstly, this paper gives the detailed elaboration of deep learning about importance, concept and characters. Then we illustrate the value and significance of deep learning. Secondly, it describes two kinds of typical deep learning models which are relatively mature at present in detail: convolution neural network, sparse auto-encoder network. We also summarize the latest application of them. Thirdly, we introduce two deep models which relatively have the potential and practical significance: multilayer kernel machines (MKMs) and deep spatiotemporal inference model. They inject fresh energy to deep learning model development. At last, we summarize the development of deep learning model trends.
Keywords: Neural Network Deep Learning Network Structure Model Comparison
基金:
论文图表:
引用
No.4605981991190140****
同行评议
共计0人参与
勘误表
深度学习最新研究进展综述
评论
全部评论0/1000