Filters








216 Hits in 5.3 sec

Kernel Density Estimation based Factored Relevance Model for Multi-Contextual Point-of-Interest Recommendation [article]

Anirban Chakraborty, Debasis Ganguly, Annalina Caputo, Gareth J. F. Jones
2021 arXiv   pre-print
We further generalize the proposed FRLM by incorporating the semantic relationships between terms in POI descriptors using kernel density estimation (KDE) on embedded word vectors.  ...  Our experiments, conducted on the TREC contextual suggestion 2016 dataset, demonstrate that factorization, KDE-based generalizations, and trip-qualifier enriched contexts of the relevance model improve  ...  : We choose word vector compositionality based relevance feedback using kernel density estimation [29] (Equation 10) as another baseline.  ... 
arXiv:2006.15679v2 fatcat:vaina2u6uza5fis722auczp5ku

Neural information retrieval: at the end of the early years

Kezban Dilek Onal, Ye Zhang, Ismail Sengor Altingovde, Md Mustafizur Rahman, Pinar Karagoz, Alex Braylan, Brandon Dang, Heng-Lu Chang, Henna Kim, Quinten McNamara, Aaron Angert, Edward Banner (+7 others)
2017 Information retrieval (Boston)  
Recent years have witnessed an explosive growth of research into NN-based approaches to information retrieval (IR). A significant body of work has now been created.  ...  Acknowledgements We would like to thank Christophe van Gysel from the University of Amsterdam, for his valuable feedback and comments.  ...  Then they estimate the kernel density of the probability density function that generates the query word embeddings. The query term can control the shape of the estimated probability density function.  ... 
doi:10.1007/s10791-017-9321-y fatcat:plrhhwkppjgb7l5r5daiyryj4q

Getting Started with Neural Models for Semantic Matching in Web Search [article]

Kezban Dilek Onal, Ismail Sengor Altingovde, Pinar Karagoz, Maarten de Rijke
2016 arXiv   pre-print
This survey is meant as an introduction to the use of neural models for semantic matching. To remain focused we limit ourselves to web search.  ...  Recent advances in language technology have given rise to unsupervised neural models for learning representations of words as well as bigger textual units.  ...  By using NCE, the probability density estimation problem is converted to a binary classification problem.  ... 
arXiv:1611.03305v1 fatcat:agdgj7allbczxcyteuomswn574

Neural Information Retrieval: A Literature Review [article]

Ye Zhang, Md Mustafizur Rahman, Alex Braylan, Brandon Dang, Heng-Lu Chang, Henna Kim, Quinten McNamara, Aaron Angert, Edward Banner, Vivek Khetan, Tyler McDonnell, An Thanh Nguyen (+3 others)
2017 arXiv   pre-print
In this work, we survey the current landscape of Neural IR research, paying special attention to the use of learned representations of queries and documents (i.e., neural embeddings).  ...  Two different methods are used for estimating the query language model: via Pseudo Relevance Feedback (PRF) (Lavrenko and Croft, 2001) , which they refer to as pseudo query vector (PQV), and via maximum-likelihood  ...  Ganguly et al. (2016) opine that: "...adding the constituent word vectors... to obtain the vector representation of the whole document is not likely to be useful, because... compositionality of the word  ... 
arXiv:1611.06792v3 fatcat:i2eqfj5l25epjcytgvifta4y4i

Hangul Fonts Dataset: a Hierarchical and Compositional Dataset for Investigating Learned Representations [article]

Jesse A. Livezey, Ahyeon Hwang, Jacob Yeung, Kristofer E. Bouchard
2021 arXiv   pre-print
Hierarchy and compositionality are common latent properties in many natural and scientific datasets.  ...  Determining when a deep network's hidden activations represent hierarchy and compositionality is important both for understanding deep representation learning and for applying deep networks in domains  ...  We are grateful for the feedback on the project from the Neural Systems and Data Science Lab.  ... 
arXiv:1905.13308v2 fatcat:tfoqcr3p25hsriqx7u2oa4pzna

Bayesian Inference of Atomic Diffusivity in a Binary Ni/Al System Based on Molecular Dynamics

F. Rizzi, M. Salloum, Y.M. Marzouk, R.-G. Xu, M. L. Falk, T. P. Weihs, G. Fritz, O. M. Knio
2011 Multiscale Modeling & simulation  
On the contrary, large discrepancies with experimental predictions are observed when D is estimated based on large-time mean-square displacement (MSD) analysis, and when it is evaluated using the Arrhenius  ...  The noise inherent in the MD simulations is described as a Gaussian process, and this hypothesis is verified both a priori and using a posterior predictive check.  ...  We repeat this procedure with four independent draws from the posterior (k = 1, . . . , 4), and compute via kernel density estimation the density of the replicated data {t n k }.  ... 
doi:10.1137/10080590x fatcat:sbudxscy7rfw5m6kagddbs45hq

Compositional Generative Mapping for Tree-Structured Data—Part II: Topographic Projection Model

D. Bacciu, A. Micheli, A. Sperduti
2013 IEEE Transactions on Neural Networks and Learning Systems  
In other words, provided that a suitable number of basis function is used, it can represent any mapping.  ...  Kernel-based models [19] , [20] are characterized by a non-adaptive metric, since this is not learned from the data, whereas it is set a priori when choosing the graph kernel.  ... 
doi:10.1109/tnnls.2012.2228226 pmid:24808278 fatcat:k3fwnsyc55hntmbyf7wwmjbmvu

A generic framework for semantic video indexing based on visual concepts/contexts detection

Nizar Elleuch, Anis Ben Ammar, Adel M. Alimi
2014 Multimedia tools and applications  
It is based on three levels of analysis.  ...  Open Access This article is distributed under the terms of the Creative Commons Attribution License which permits any use, distribution, and reproduction in any medium, provided the original author(s)  ...  In addition, we have introduced a relevance feedback process by jointly exploiting annotated and unannotated data.  ... 
doi:10.1007/s11042-014-1955-9 fatcat:qd2rn5x7pzgstje32nffgigkru

Holistic Entropy Reduction for Collaborative Filtering

Andrzej Szwabe, Pawel Misiorek, Tadeusz Janasiewicz, Przemyslaw Walkowiak
2014 Foundations of Computing and Decision Sciences  
As shown in the experiments presented in the paper, the compositionality of the vector-space representations allows an HPMPP-based recommendation system to identify which of the unknown facts having the  ...  The dual graph-vector representation of the available propositional data enables the entropy-reducing transformation and supports the compositionality of mutually compatible representations.  ...  In other words, as far as the vector-space graph nodes representations are concerned, the application of SVD imposes entropy constraints that are avoidable when the HPMPP method is used.  ... 
doi:10.2478/fcds-2014-0012 fatcat:tbdyqe4xureh3nqgao7vsiw4na

Automated Verification and Synthesis of Stochastic Hybrid Systems: A Survey [article]

Abolfazl Lavaei, Sadegh Soudjani, Alessandro Abate, Majid Zamani
2022 arXiv   pre-print
Stochastic hybrid systems have received significant attentions as a relevant modelling framework describing many systems, from engineering to the life sciences: they enable the study of numerous applications  ...  The tool is implemented in C++ and employs manipulations based on vector calculus, using sparse matrices, the symbolic construction of probabilistic kernels, and multithreading.  ...  Given N vectors x i ∈ R ni , n i ∈ N ≥1 , and i ∈ {1, . . . , N }, we use x = [x 1 ; . . . ; x N ] to denote the corresponding column vector of dimension i n i .  ... 
arXiv:2101.07491v2 fatcat:dpir554ebfclhpj5m7e7fi2hv4

Comprehensive machine learning analysis of Hydra behavior reveals a stable basal behavioral repertoire

Shuting Han, Ekaterina Taralova, Christophe Dupre, Rafael Yuste
2018 eLife  
Here, we developed an automatic behavior analysis pipeline for the cnidarian Hydra vulgaris using machine learning.  ...  Using this analysis pipeline, we quantified 6 basic behaviors and found surprisingly similar behavior statistics across animals within the same species, regardless of experimental conditions.  ...  This material is based upon work supported by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-17-C-0026.  ... 
doi:10.7554/elife.32605 pmid:29589829 pmcid:PMC5922975 fatcat:yyaxmyji5bb3jggjdjznznkz7i

NeuroQuery, comprehensive meta-analysis of human brain mapping

Jérôme Dockès, Russell A Poldrack, Romain Primet, Hande Gözükan, Tal Yarkoni, Fabian Suchanek, Bertrand Thirion, Gael Varoquaux
2020 eLife  
We then use Gaussian Kernel Density Estimation (KDE) [Silverman, 1986 , Scott, 2015 695 to estimate the density of these activations over the brain.  ...  We automatically extract 418 772 peak 151 activations coordinates from publications, and transform them to brain maps with a kernel density 152 estimator.  ...  matches of multi-word expressions such as "creative problem solving", " facial trustworthiness 1018 recognition ", "positive feedback processing", "potential monetary reward", "visual word recognition"  ... 
doi:10.7554/elife.53385 pmid:32129761 pmcid:PMC7164961 fatcat:hvjkw5qurbgnneqwgl5ew4pafq

The geometry of domain-general performance monitoring representations in the human medial frontal cortex [article]

Zhongzheng Fu, Danielle Beam, Jeffrey M. Chung, Chrystal M. Reed, Adam N. Mamelak, Ralph Adolphs, Ueli Rutishauser
2021 bioRxiv   pre-print
Neurons encoding conflict ex-post served to iteratively update internal estimates of control demand as predicted by a Bayesian model.  ...  These findings reveal how the MFC representation of evaluative signals are both abstract and specific, suggesting a mechanism for computing and maintaining control demand estimates across trials and tasks  ...  We used the linear kernel and set the ܿ parameter to 1 for all analyses.  ... 
doi:10.1101/2021.07.08.451594 fatcat:jszwrozcsrb7tk2jqby5y3uljq

On-line Adaptative Curriculum Learning for GANs [article]

Thang Doan, Joao Monteiro, Isabela Albuquerque, Bogdan Mazoure, Audrey Durand, Joelle Pineau, R Devon Hjelm
2019 arXiv   pre-print
We also draw connections between our algorithm and stochastic optimization methods and then show that existing approaches using multiple discriminators in literature can be recovered from our framework  ...  formalize this problem within the full-information adversarial bandit framework, where we evaluate the capability of an algorithm to select mixtures of discriminators for providing the generator with feedback  ...  Let p(x) denote the target density 2 , and let p(z) denote the prior density defined on Z used to draw noise samples for input into the generator.  ... 
arXiv:1808.00020v6 fatcat:3m3xyevomrhlzlydgefnoodeii

A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges [article]

Denis Kleyko, Dmitri A. Rachkovskij, Evgeny Osipov, Abbas Rahimi
2022 arXiv   pre-print
structured symbolic representations and vector distributed representations.  ...  The survey is written to be useful for both newcomers and practitioners.  ...  To do so, for each word authors represented its most relevant semantic features taken from a knowledge base ConceptNet.  ... 
arXiv:2112.15424v2 fatcat:uteoq33hgna2fhs2o46rkde2iq
« Previous Showing results 1 — 15 out of 216 results