Affiliation:
1. National Institute of Technology, Kurukshetra, India
Abstract
The high-tech world we live in today is dominated by multimedia. Multimedia is being created at a rapid rate in the current technological era. Consumption and the exchange of the same between users happen quickly. Choosing whatever form of content or multimedia to consume next depending on interests and preferences is a conundrum while consuming this content. Nowadays, all online streaming sites utilize multimedia recommender systems. These are utilized to anticipate the following collection of multimedia that users can enjoy based on their prior usage patterns. By identifying the points of commonality between the user and the goods, preexisting models can forecast this utilizing the collaborative field. By treating this as a sequence prediction problem, the proposed model in this chapter increases the predicted accuracy using collaborative filtering (CF), ripple nets, deep learning, and recurrent neural networks (RNNs).
Reference22 articles.
1. Adadelta, M. D. (2012). An adaptive learning rate method. arXiv preprint arXiv:1212.5701.
2. Bernhardsson. E. (2014). Recurrent neural networks for collaborative filtering. arXiv preprint.
3. Brafman, R. I., Heckerman, D., & Shani, G. (2000). Recommendation as a stochastic sequential decision problem. In ICAPS, 164–173.
4. Recurrent neural network language model training with noise contrastive estimation for speech recognition
5. Cho, K., Merrienboer, B. V., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. In Proceedings of SSST@EMNLP 2014,Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation. IEEE..
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. AI Business Boost Approach for Small Business and Shopkeepers;Advances in Business Information Systems and Analytics;2024-01-04