|
|
Review on development of deep learning |
School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China |
|
|
Abstract To solve the insufficiency of shallow learning expression ability and the excessive dimension disaster due to the feature dimension, deep learning was used due to the unique hierarchies and capability of extracting high level features from lowlevel features, and brought new hope for artificial intelligence. The development of deep learning during different periods was introduced. The basic models of RBM, AE and CNN were analyzed to present the deep hierarchical structures of DBN, DBM and SAE. The applications of deep learning in the fields of speech recognition, computer vision, natural language processing and information retrieval in recent years were introduced to illustrate the superiority and flexibility of deep learning compared with other shallow learning algorithms. Some future research directions were predicted based on the analysis, and some conclusions were made according to the improvement of deep learning on algorithm generalization, adaptation of big data and modifying on deep structure.
|
Received: 08 May 2014
|
|
|
|
|
|
|