Filters








115 Hits in 8.6 sec

CAFE

Yikun Xian, Zuohui Fu, Handong Zhao, Yingqiang Ge, Xu Chen, Qiaoying Huang, Shijie Geng, Zhou Qin, Gerard de Melo, S. Muthukrishnan, Yongfeng Zhang
2020 Proceedings of the 29th ACM International Conference on Information & Knowledge Management  
To this end, we propose a CoArse-to-FinE neural symbolic reasoning approach (CAFE).  ...  It first generates user profiles as coarse sketches of user behaviors, which subsequently guide a path-finding process to derive reasoning paths for recommendations as fine-grained predictions.  ...  ACKNOWLEDGEMENT The authors thank the reviewers for the valuable comments and constructive suggestions. This work was supported in part by NSF IIS-1910154.  ... 
doi:10.1145/3340531.3412038 dblp:conf/cikm/XianFZGCHG0MMZ20 fatcat:a3z63vre6rcezcupmqxlr34b3a

Path Language Modeling over Knowledge Graphsfor Explainable Recommendation

Shijie Geng, Zuohui Fu, Juntao Tan, Yingqiang Ge, Gerard de Melo, Yongfeng Zhang
2022 Proceedings of the ACM Web Conference 2022  
By reasoning over a KG in a node-by-node manner, existing explainable models provide a KG-grounded path for each user-recommended item.  ...  Moreover, the proposed technique makes it possible to conduct explainable recommendation even when the KG is sparse or possesses a large number of relations.  ...  Any opinions, findings, conclusions or recommendations expressed in this material are those of the authors and do not necessarily reflect those of the sponsors.  ... 
doi:10.1145/3485447.3511937 fatcat:3tqe4t4uqzedljhq3xhs2lfnj4

Vis-CRF, A Classical Receptive Field Model for VISION [article]

Nasim Nematzadeh, David MW Powers, Trent Lewis
2020 arXiv   pre-print
sent to the cortex for further processing.  ...  Based on these neurobiological discoveries, in our previous work, we provided computer simulation evidence to suggest that Geometrical illusions are explained in part, by the interaction of multiscale  ...  The ratio of 1:1.6 is given by Marr and Hildreth (1980) for modelling retinal GCs in general, and Earle and Maskell (1993) used this ratio for DoG modelling specifically to explain the Café Wall illusion  ... 
arXiv:2011.08363v1 fatcat:zpj7sznbfrarda4jwirux577wu

Large Scale Question Answering using Tourism Data [article]

Danish Contractor and Krunal Shah and Aditi Partap and Mausam and Parag Singla
2020 arXiv   pre-print
This dataset is especially challenging because commonly used neural architectures for reasoning and QA are prohibitively expensive for a task of this scale.  ...  It first clusters text for each entity to identify exemplar sentences describing an entity.  ...  We would like to thank Shashank Goel for re-implementing the data collection scripts and maintaining the GitHub repository.  ... 
arXiv:1909.03527v2 fatcat:td7w4bsldrfbnhxn6rhxj2h3ka

Deflationary realism: Representation and idealisation in cognitive science

Dimitri Coelho Mollo
2021 Mind & Language  
ACKNOWLEDGEMENTS I am indebted to Nicholas Shea, Michael Pauen, Mark Sprevak, Margherita Arcangeli, and the audience of the workshop on Representation in Cognitive Science, Bochum 2020, for helpful comments  ...  Third, and relatedly, several of the relevant causal factors for explaining intelligent behaviour-for example, fine-grained neural workings, evolutionary history-are either currently or in principle epistemically  ...  the cafe is excellent and I am hungry, etc.).  ... 
doi:10.1111/mila.12364 fatcat:xn5juqoasfct3ekbocsfadqxvy

Neural graph reasoning for explainable decision-making

Yikun Xian
2021
explanations, which is also known as the neural graph reasoning for explainable decision-making.  ...  Unlike existing work on explainable machine learning that mainly yields model-agnostic explanations for deep neural networks, we attempt to develop intrinsically interpretable models based on graphs with  ...  More human-involved tasks that requires both high accuracy and trustable explainability can be explored under the graph reasoning framework.  ... 
doi:10.7282/t3-bpj3-ng33 fatcat:ysf3yu5ynjcnhalk7vx5p6rsii

Point-of-interest lists and their potential in recommendation systems

Giorgos Stamatelatos, George Drosatos, Sotirios Gyftopoulos, Helen Briola, Pavlos S. Efraimidis
2021 Information Technology & Tourism  
Location based social networks, such as Foursquare and Yelp, have inspired the development of novel recommendation systems due to the massive volume and multiple types of data that their users generate  ...  Our hypothesis is that the information encoded in the lists can be utilized to estimate the similarities amongst POIs and, hence, these similarities can drive a personalized recommendation system or enhance  ...  We would also like to thank the anonymous reviewers who helped us improve our work, and especially for suggesting the offline experiment of Section 5.3.  ... 
doi:10.1007/s40558-021-00195-5 fatcat:z26fhtad7fhvvgok7hpu7umage

Is what you feel what you don't know?

Simon C. Moore, Mike Oaksford
2000 Behavioral and Brain Sciences  
); a theory of consciousness and its application to understanding emotion and pleasure (Ch. 9); and neural networks and emotion-related learning (Appendix).  ...  reward, 6 for addiction, 7 for thirst, and 8 for sexual behavior.  ...  versus coarse coding of knowledge .  ... 
doi:10.1017/s0140525x00422429 fatcat:adhl36avcfhgzmoppkbxftk2xq

Précis of The brain and emotion

Edmund T. Rolls
2000 Behavioral and Brain Sciences  
); a theory of consciousness and its application to understanding emotion and pleasure (Ch. 9); and neural networks and emotion-related learning (Appendix).  ...  reward, 6 for addiction, 7 for thirst, and 8 for sexual behavior.  ...  versus coarse coding of knowledge .  ... 
doi:10.1017/s0140525x00002429 fatcat:yun6yjzk5vestlymq7d2dsdzji

Deep Latent-Variable Models for Text Generation [article]

Xiaoyu Shen
2022 arXiv   pre-print
Text generation aims to produce human-like natural language output for down-stream tasks.  ...  Recently deep neural network-based end-to-end architectures have been widely adopted.  ...  For example, we can perform a similar constrained decoding as in Balakrishnan et al. (2019) to rule out outputs with undesired patterns.19 Coarse-to-fine attention was proposed for the same motivation  ... 
arXiv:2203.02055v1 fatcat:sq3upxl7xvfnhigoc7apszomwu

Image Steganography Using HBC and RDH Technique

Hemalatha M, Prasanna A, Dinesh Kumar R, Vinothkumar D
2014 International Journal of Computer Applications Technology and Research  
Here Integer Cosine Transform (ICT) and Integer Wavelet Transform (IWT) is combined for converting signal to frequency.  ...  Hide Behind Corner (HBC) algorithm is used to place a key at corners of the image. All the corner keys are encrypted by generating Pseudo Random Numbers. The Secret keys are used for corner parts.  ...  ACKNOWLEDGEMENTS Our thanks to the colleague Lecturers of Computer Science department Federal College of Education (Technical) Potiskum for their contributions towards development of the paper.  ... 
doi:10.7753/ijcatr0303.1001 fatcat:4i6tujs4oje2tnxf5c25eh26x4

Sparsity-aware neural user behavior modeling in online interaction platforms [article]

Aravind Sankar
2022 arXiv   pre-print
In this dissertation, we develop generalizable neural representation learning frameworks for user behavior modeling designed to address different sparsity challenges across applications.  ...  Our proposed models are complementary to concurrent advances in neural architectural choices and are adaptive to the rapid addition of new applications in online platforms.  ...  , with consistent gains for the variants of all neural base recommenders.  ... 
arXiv:2202.13491v1 fatcat:5lhvre4kpzao5ow7gvxa2qnwhq

Inducing semantic relations from conceptual spaces: A data-driven approach to plausible reasoning

Joaquín Derrac, Steven Schockaert
2015 Artificial Intelligence  
Commonsense reasoning patterns such as interpolation and a fortiori inference have proven useful for dealing with gaps in structured knowledge bases.  ...  An important di culty in applying these reasoning patterns in practice is that they rely on fine-grained knowledge of how di↵erent concepts and entities are semantically related.  ...  In this paper, we essentially view point based representations as coarse-grained approximations of conceptual spaces, where points correspond to fine-grained categories instead of specific instances, while  ... 
doi:10.1016/j.artint.2015.07.002 fatcat:3m6qpscx3rforjr23ltil2wl4i

JKR adhesive contact for a transversely isotropic layer of finite thickness

I I Argatov, F M Borodich, V L Popov
2015 Journal of Physics D: Applied Physics  
Commonsense reasoning patterns such as interpolation and a fortiori inference have proven useful for dealing with gaps in structured knowledge bases.  ...  An important di culty in applying these reasoning patterns in practice is that they rely on fine-grained knowledge of how di↵erent concepts and entities are semantically related.  ...  In this paper, we essentially view point based representations as coarse-grained approximations of conceptual spaces, where points correspond to fine-grained categories instead of specific instances, while  ... 
doi:10.1088/0022-3727/49/4/045307 fatcat:hzau2pp3yne3nadakbj3boctra

Crowding is similar for eye movements and manual responses

F. Yildirim, F. W. Cornelissen
2014 Journal of Vision  
Differences Hugh R Wilson 54.17, 4:00 pm Solving stereo transparency with an extended coarse-to-fine disparity energy model Zhe Li, Ning Qian Object attention in moderate precision tasks: Mechanisms of  ...  -6:45 pm Poster Session, Pavilion 26.566 Prediction of perceived fog density and defogging of natural foggy images Lark Kwon Choi, Jaehee You, Alan Bovik 26.567 Does RMS contrast normalization impair coarse-to-fine  ... 
doi:10.1167/14.10.789 fatcat:uxwzbzfhbjc3ddyfhbs2ilr4qe
« Previous Showing results 1 — 15 out of 115 results