论文信息 - Ukiyo-e recommender system using restricted boltzmann machine

Ukiyo-e recommender system using restricted boltzmann machine

In this study, we implement an Ukiyo-e recommender system based on a restricted Boltzmann machine (RBM) for recommending Ukiyo-e prints to Ukiyo-e novices. This system can solve the problem of searching Ukiyo-e prints using keywords that are known only to Ukiyo-e experts. This system thus enables even an Ukiyo-e novice to obtain appropriate Ukiyo-e prints based on his interests. The user selects his interests amongst the few prints that are displayed initially. Then, with the use of an RBM, the system can find prints that match the user's interests. It can reconstruct the content information before making any recommendations.

Kyoji Kawagoe | Jiayun Wang

[1] Gediminas Adomavicius,et al. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions , 2005, IEEE Transactions on Knowledge and Data Engineering.

[2] Yi Yang,et al. A Kind of Precision Recommendation Method for Massive Public Digital Cultural Resources: A Preliminary Report , 2016, 2016 IEEE Second International Conference on Multimedia Big Data (BigMM).

[3] Geoffrey E. Hinton,et al. Restricted Boltzmann machines for collaborative filtering , 2007, ICML '07.

[4] Geoffrey E. Hinton,et al. ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5] Andrew Y. Ng,et al. Convolutional-Recursive Deep Learning for 3D Object Classification , 2012, NIPS.

[6] Geoffrey E. Hinton. A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[7] Dit-Yan Yeung,et al. Collaborative Deep Learning for Recommender Systems , 2014, KDD.

[8] Yoshua Bengio,et al. Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[9] Kyoji Kawagoe,et al. Ukiyo-e Recommendation based on Deep Learning For Learning Japanese Art and Culture , 2017, ICISDM '17.