Filters








15,777 Hits in 9.0 sec

On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)

Vincent Francois-Lavet, Guillaume Rabusseau, Joelle Pineau, Damien Ernst, Raphael Fonteneau
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
When an agent has limited information on its environment, the suboptimality of an RL algorithm can be decomposed into the sum of two terms: a term related to an asymptotic bias (suboptimality with unlimited  ...  In the context of reinforcement learning with partial observability, this paper provides an analysis of the tradeoff between these two error sources.  ...  proposed a hierarchical Bayesian model called collaborative deep learning (CDL) which tightly couples stacked denoising auto-encoders (SDA) and collaborative topic regression (CTR).  ... 
doi:10.24963/ijcai.2020/695 dblp:conf/ijcai/0001Z20 fatcat:yx2wihhuobgmjjh4aevkbr33g4

Explainable Recommendation: A Survey and New Perspectives [article]

Yongfeng Zhang, Xu Chen
2020 arXiv   pre-print
The explanations may either be post-hoc or directly come from an explainable model (also called interpretable or transparent model in some contexts).  ...  We then conduct a comprehensive survey of explainable recommendation on three perspectives: 1) We provide a chronological research timeline of explainable recommendation. 2) We provide a two-dimensional  ...  (2018a) leveraged neural attention regression based on reviews to conduct rating prediction on three Amazon product categories; Chen et al. (2018c) adopted memory networks to provide explainable sequential  ... 
arXiv:1804.11192v10 fatcat:scsd3htz65brbiae35zd3nixe4

Sequential Pattern Mining Model to Identify the Most Important or Difficult Learning Topics via Mobile Technologies

Edona Doko, Lejla Abazi Bexheti, Mentor Hamiti, Blerta Prevalla Etemi
2018 International Journal of Interactive Mobile Technologies  
Based on this method, it is designed a model for understanding and learning the most difficult topics of students topics.  ...  The paper mainly describes the model for understanding and learning the most difficult topics through the sequential pattern mining method.  ...  Clustering can be used in any domain that involves classifying, even to determine how much collaboration users exhibit based on postings in discussion forums.  ... 
doi:10.3991/ijim.v12i4.9223 fatcat:abxu3gexsnettlffw7nuuo5vgq

Coevolutionary Recommendation Model

Yichao Lu, Ruihai Dong, Barry Smyth
2018 Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18  
recommendation approach that relies on user-item ratings.  ...  In this paper, we present a novel deep learning recommendation model, which co-learns user and item information from ratings and customer reviews, by optimizing matrix factorization and an attention-based  ...  (iv) CTR: Collaborative Topic Regression (CTR) [41] learns interpretable latent structure from user generated content so that probabilistic topic modeling can be integrated into collaborative filtering  ... 
doi:10.1145/3178876.3186158 dblp:conf/www/LuDS18 fatcat:bpixoia46vftvb2albidnhzjvy

A Synthesis of Current Surveillance Planning Methods for the Sequential Monitoring of Drug and Vaccine Adverse Effects Using Electronic Health Care Data

Jennifer C. Nelson, Robert Wellman, Onchee Yu, Andrea J. Cook, Judith C. Maro, Rita Ouellet-Hellstrom, Denise Boudreau, James S. Floyd, Susan R. Heckbert, Simone Pinheiro, Marsha Reichman, Azadeh Shoaibi
2016 eGEMs  
Future Surveillance Planning: Based on this examination, we suggest three steps for future surveillance planning in health care databases: (1) prespecify the sequential design and analysis plan, using  ...  Future Surveillance Planning: Based on this examination, we suggest three steps for future surveillance planning in health care databases: (1) prespecify the sequential design and analysis plan, using  ...  electronic health care databases, which contributes to an emerging literature on this topic  ... 
doi:10.13063/2327-9214.1219 pmid:27713904 pmcid:PMC5051582 fatcat:74i2p3hu75h6hjhxpjsnb3smsq

Deep Learning based Recommender System: A Survey and New Perspectives [article]

Shuai Zhang, Lina Yao, Aixin Sun, Yi Tay
2018 arXiv   pre-print
Evidently, the field of deep learning in recommender system is flourishing. This article aims to provide a comprehensive review of recent research efforts on deep learning based recommender systems.  ...  With the ever-growing volume of online information, recommender systems have been an effective strategy to overcome such information overload.  ...  Modelling sequential signals is an important topic for mining the temporal dynamics of user behaviour and item evolution.  ... 
arXiv:1707.07435v6 fatcat:2q2dbfy2jvdydhbrmmbyrzctnq

Seek for Success: A Visualization Approach for Understanding the Dynamics of Academic Careers [article]

Yifang Wang, Tai-Quan Peng, Huihua Lu, Haoren Wang, Xiao Xie, Huamin Qu, Yingcai Wu
2021 arXiv   pre-print
A novel timeline is designed to reveal and compare the factor impacts based on the whole population.  ...  We first applied a Multi-factor Impact Analysis framework to estimate the effect of different factors on academic career success over time.  ...  P B wanted more interpretations related to the regression model.  ... 
arXiv:2108.03381v2 fatcat:35vlbzsmfvgupctfrledshdice

A Hybrid Recommender System for Recommending Smartphones to Prospective Customers [article]

Pratik K. Biswas, Songlin Liu
2021 arXiv   pre-print
Some hybrid recommender systems have combined collaborative filtering and content-based approaches to build systems that are more robust.  ...  In this paper, we propose a hybrid recommender system, which combines Alternative Least Squares (ALS) based collaborative filtering with deep learning to enhance recommendation performance as well as overcome  ...  Discussion: Modeling sequential signals is an important topic for mining the temporal dynamics of visitor behavior and device evolution.  ... 
arXiv:2105.12876v1 fatcat:6q3wpnmkerd7pnnpsfhvbilxca

Dynamic Intention-Aware Recommendation System [article]

Shuai Zhang, Lina Yao
2017 arXiv   pre-print
Recommender systems have been actively and extensively studied over past decades. In the meanwhile, the boom of Big Data is driving fundamental changes in the development of recommender systems.  ...  In this paper, we propose a dynamic intention-aware recommender system to better facilitate users to find desirable products and services.  ...  HMM is an e cient dynamic tool for modelling sequential data.  ... 
arXiv:1703.03112v2 fatcat:af3jq4emcna6heoyujwxwqdmgu

Survey for Trust-aware Recommender Systems: A Deep Learning Perspective [article]

Manqing Dong, Feng Yuan, Lina Yao, Xianzhi Wang, Xiwei Xu, Liming Zhu
2020 arXiv   pre-print
We focus on the work based on deep learning techniques, an emerging area in the recommendation research.  ...  This survey provides a systemic summary of three categories of trust-aware recommender systems: social-aware recommender systems that leverage users' social relationships; robust recommender systems that  ...  [116] propose an adversarial training framework for recommendation. The model is designed based on the collaborative denoising autoencoder.  ... 
arXiv:2004.03774v2 fatcat:q7mehir7hbbzpemw3q5fkby5ty

Learning Management System with Prediction Model and Course-content Recommendation Module

2017 Journal of Information Technology Education  
the leaners profile; developing of an algorithm for generating predictions; and making the most appropriate recommendations for the learners based on prior knowledge and learning styles.  ...  Background: It utilized five-year historical data to find patterns for predicting student performance in Java Programming to generate appropriate course-content recommendations for the students based on  ...  Aside from the usual way of simply recommending learning topics, recommendations on how the learner could make the most out of the learning experience are also provided.  ... 
doi:10.28945/3883 fatcat:cptwhvxdejcchfqo6w2ierkywi

Recommender Systems In Social Networks

Cleomar Valois, Marcius Armada
2011 Journal of Information Systems and Technology Management  
Developing a recommender system that takes into account the social network of the user is another way of tackling the problem.  ...  The continued and diversified growth of social networks has changed the way in which users interact with them.  ...  Collaborative filtering based on users predicts user interest in an item based on evaluations of similar users (J., D. and C. 1998) (J., et al. 1999) .  ... 
doi:10.4301/s1807-17752011000300009 fatcat:nsmcoejszbfdrhbp5xuiu75ery

Data Science in Service of Performing Arts: Applying Machine Learning to Predicting Audience Preferences [article]

Jacob Abernethy, Cyrus Anderson (University of Michigan), Alex Chojnacki, Chengyu Dai, Eric Schwartz, Jonathan Stroud , Sheng Yang
2016 arXiv   pre-print
We built a recommendation system based on collaborative filtering, gaining insights into the artistic preferences of customers, along with the similarities between performances.  ...  Success relies on understanding audience preference and predicting their behavior.  ...  This work is supported by the National Science Foundation under CAREER grant IIS-1453304, an award that helped facilitate the development of the Michigan Data Science Team.  ... 
arXiv:1611.05788v1 fatcat:l2i6a7ftwvao5gtbhjryfthqiy

Context-Aware Recommender Systems for Social Networks: Review, Challenges and Opportunities

Areej Bin Suhaim, Jawad Berri
2021 IEEE Access  
The paper presents the detail of the review study, provides a synthesis of the results, proposes an evaluation based on measurable evaluation tools developed in this study, and advocates future research  ...  Primary research articles selected are reviewed and the recommendation process is analyzed to identify the approach, the techniques, and the context elements employed in the development of the recommendation  ...  A joint probabilistic latent factor model presented in the micro-topics recommendation [64] is built on top of collaborative filtering, content analysis, and feature regression to blend rich information  ... 
doi:10.1109/access.2021.3072165 fatcat:i3igbxd44jhrzcyvynevpidcwq

Word Sequential Using Deep LSTM and Matrix Factorization to Handle Rating Sparse Data for E-Commerce Recommender System

Hanafi, Burhanuddin Mohd Aboobaider, Amparo Alonso-Betanzos
2021 Computational Intelligence and Neuroscience  
According to the experiment report, this model significantly outperformed the traditional latent factor model by more than 16% on an average and achieved 1% on an average based on RMSE evaluation metrics  ...  Collaborative filtering is a type of recommender system model that uses customers' activities in the past, such as ratings.  ...  Acknowledgments is research was fully supported and funded by an internal grant from Universitas Amikom Yogyakarta.  ... 
doi:10.1155/2021/8751173 pmid:34917141 pmcid:PMC8670980 fatcat:tllcbuvfvjbj3dgpp7rhivvdv4
« Previous Showing results 1 — 15 out of 15,777 results