Video recommendation system provides users with suitable video for users to choose, which is an effective way to get a higher user satisfaction and user stickiness. Therefore, video websites pay much attention to it, as well as scholars. The existing recommendation algorithms are fused machine learning algorithms to video recommendation system. Such as some studies the SVM algorithm combined with a recommendation algorithm based on content, or use the BP neural network combined with collaborative filtering algorithm, to improve the algorithm accuracy. With the rapid development of Machine Learning, progresses in Deep Learning are considerable. Especially after the RBM training efficiency matter has been solved by the random sample, the reliability of multi-layer neural network is more clearly, also caused academic interest in depth of the neural network research. Compared to the original SVM model or Shallow Neural Network, Deep Neural Network has a more comprehensive structure, which leads to a better performance in function approximation and feature extraction. Apparently, if Deep Neural Network algorithm is deployed to recommend videos, a better accuracy will be achieved. This paper proposes a video recommendation system, which combines DBN with Collaborative Filtering algorithm, experimental results show that our algorithm achieves a better performance in accuracy compared with old ones.
[1]
Jason Weston,et al.
A unified architecture for natural language processing: deep neural networks with multitask learning
,
2008,
ICML '08.
[2]
Thore Graepel,et al.
Matchbox: large scale online bayesian recommendations
,
2009,
WWW '09.
[3]
Deng Ai,et al.
A Collaborative Filtering Recommendation Algorithm Based on Item Rating Prediction
,
2003
.
[4]
Abhinandan Das,et al.
Google news personalization: scalable online collaborative filtering
,
2007,
WWW '07.
[5]
Raymond J. Mooney,et al.
Content-boosted collaborative filtering for improved recommendations
,
2002,
AAAI/IAAI.
[6]
Dong Yu,et al.
Conversational Speech Transcription Using Context-Dependent Deep Neural Networks
,
2012,
ICML.
[7]
Hossein Mobahi,et al.
Deep Learning via Semi-supervised Embedding
,
2012,
Neural Networks: Tricks of the Trade.
[8]
Jason Weston,et al.
Deep learning via semi-supervised embedding
,
2008,
ICML '08.
[9]
Yee Whye Teh,et al.
A Fast Learning Algorithm for Deep Belief Nets
,
2006,
Neural Computation.
[10]
Xia Ke,et al.
An Optimization Algorithm on the Number of Hidden Layer Nodes in Feed-forward Neural Network
,
2005
.