Filters








13 Hits in 6.7 sec

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
We discuss deep reinforcement learning in an overview style. We draw a big picture, filled with details.  ...  Next we discuss RL core elements, including value function, policy, reward, model, exploration vs. exploitation, and representation.  ...  The authors present an implementation with centralized training for decentralized execution, as discussed below. The authors experiment with grid world coordination, a partially observable game,  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

CARS 2016—Computer Assisted Radiology and Surgery Proceedings of the 30th International Congress and Exhibition Heidelberg, Germany, June 21–25, 2016

2016 International Journal of Computer Assisted Radiology and Surgery  
'', and Amazon Inc., for providing valuable computing resources through an ''AWS in Education Research'' grant.  ...  We would like to thank the Spanish company BQ for the donation of the 3D printing hardware for clinical use.  ...  If the number of bands is odd, then this will cover both the first and last bands, and thus every vertex will be accounted for.  ... 
doi:10.1007/s11548-016-1412-5 pmid:27206418 fatcat:uk5r46n2xvhedkfjzmeiweyneq

A topological solution to object segmentation and tracking [article]

Thomas Tsao, Doris Y. Tsao
2021 arXiv   pre-print
Here, we show that the mathematical structure of light rays reflected from environment surfaces yields a natural representation of persistent surfaces, and this surface representation provides a solution  ...  We describe how to generate this surface representation from continuous visual input, and demonstrate that our approach can segment and invariantly track objects in cluttered synthetic video despite severe  ...  Acknowledgements The concept of topological information processing as a major component of vision has far reaching consequences for our understanding of how biological vision functions and how computational  ... 
arXiv:2107.02036v1 fatcat:wjrncvg4angrzcnpgscfuwriwa

Estimates for Fourier sums and eigenvalues of integral operators via multipliers on the sphere

T. Jordão, V. A. Menegatto
2015 Proceedings of the American Mathematical Society  
defined by a parameterized family of multipliers operators on L 2 (S m ), as that defined in (1) .  ...  vertex-transitive graph has a hamiltonian path.  ...  In our model the problem is on the the likelihood function. The Bayesian approach was considered and some Monte Carlo Markov Chain (MCMC) algorithms have been developed.  ... 
doi:10.1090/proc12716 fatcat:5qihvaioezbztkdytpvfl3qsii

Mining, Modeling and Predicting Mobility

Mohamed Kafsi
2015
Among the probabilistic models, the Markov chain is a very popular model for mobility. Song et al.  ...  In this thesis, we take a predictive approach, based on probabilistic models, to model human mobility.  ...  Our approach, which is based on a probabilistic hierarchical model, uncovers features that are characteristic of a neighborhood.  ... 
doi:10.5075/epfl-thesis-6662 fatcat:f6j34zqv7besdfqt65gomeupl4

Artificial Intelligence and Decision Making

Stephane Herbin, Jean-Loup Farges, Valentina Dragos, Gatepaille Sylvain, Romain Kervarc, Piel Ariane, Amal El Fallah Seghrouchni, Ludovic Grivault, Florent Teichteil-Koenigsbuch, Guillaume Poveda, Cedric Pralet, Stephanie Roussel (+27 others)
2020
AI is a research field with a complex history and numerous areas.  ...  Artificial Intelligence (AI) is currently an inescapable keyword in computer science given its predicted huge contribution to the global economy [1] or to the whole society [2, 3], as argued in many recent  ...  data used in this study, and the IEEE GRSS Image Analysis and Data Fusion Technical Committee.  ... 
doi:10.12762/2020.al15 fatcat:6zlp4tbi5vckrfmxr64tusnjse

A Novel Flavour Tagging Algorithm using Machine Learning Techniques and a Precision Measurement of the B0-AntiB0 Oscillation Frequency at the LHCb Experiment

Katharina Kreplin
2015
The second number corresponds to a readjustment of the algorithm to the B 0 s production topology. This algorithm is employed in the precision measurement of ∆m d .  ...  This thesis presents a novel flavour tagging algorithm using machine learning techniques and a precision measurement of the B 0 -B 0 oscillation frequency ∆m d using semileptonic B 0 decays.  ...  .: Fundamental particles and force carriers of the Standard Model; stickers available at CERN gift shop. Figure 1 . 1 2.: Unitarity triangle, see equation 1.6, in theρ −η plane.  ... 
doi:10.11588/heidok.00018896 fatcat:ekuvjcvyo5auxge4j5syf733qi

Interaction capture and synthesis of human hands [article]

Paul G. Kry
2005
New interactions are synthesized through simulation of a quasi-static compliant articulated model in a dynamic environment that includes friction.  ...  This thesis addresses several issues in modelling interaction with human hands in computer graphics and animation.  ...  Consistent Parameterization A consistent parameterization across all scans is a prerequisite for analysis.  ... 
doi:10.14288/1.0051709 fatcat:vvwtwrmbrfba3fh6ik3uiftbii

Electronic Markets and Auctions (Dagstuhl Seminar 13461) Computational Models of Language Meaning in Context (Dagstuhl Seminar 13462) Synchronous Programming (Dagstuhl Seminar 13471) Global Measurement Framework (Dagstuhl Seminar 13472) Unleashing Operational Process Mining (Dagstuhl Seminar 13481) Forensic Computing (Dagstuhl Seminar 13482)

Saul Greenberg, Kasper Hornbaek, Aaron Quigley, Harald Reiterer, Roman, Yishay Mansour, Benny Moldovanu, Noam Nisan, Berthold, Hans Kamp, Alessandro Lenci, James (+14 others)
2013 unpublished
The seminar can be seen as a good starting point to identify the role of Proxemics in Human-Computer Interaction.  ...  However, it still remains an open research area and its place in HCI needs to be better understood. Acknowledgements.  ...  In a probabilistic Kripke model M , in a world w for an agent a, this gets a probability P a,w .  ... 
fatcat:fl5xhx4dpbeklg6o6xhmuvuety

Representation Learning for Web Intelligence

Yixuan Li
2017
This thesis work contributes to the field of machine learning in both algorithmic foundations and practical advances. The first part focuses on classification  ...  hand, it provides us with an automated means for comprehension of concrete web contents such as texts, images and audios.  ...  The DEMON algorithm [42] , for example, democratically lets each vertex vote for the communities it sees surrounding it in its limited view of the global system using a label propagation algorithm, and  ... 
doi:10.7298/x4mc8x70 fatcat:cp6svdzywvgcjovgmmpomkbt3a

Proposition-based summarization with a coherence-driven incremental model

Yimai Fang, Apollo-University Of Cambridge Repository, Apollo-University Of Cambridge Repository, Simone Teufel
2019
Summarization models which operate on meaning representations of documents have been neglected in the past, although they are a very promising and interesting class of methods for summarization and text  ...  Second, I have devised algorithms to numerically evaluate alternative ways of adding a new proposition, as well as to predict necessary changes in the tree.  ...  The LC model has four variants (LC-0, 1, 2, 3), which are parameterized differently as defined in Section 4.3.  ... 
doi:10.17863/cam.34773 fatcat:35pi5lpvvzbmrdkn7w24ynt3zi

2008 ANNUAL REPORT

AA.VV
2009
The module then is finalized by applying a layer of black sticker on its sides for light insulation.  ...  This algorithm will not necessarily be the final algorithm but is used a first reference for the clustering performances.  ...  For the the list of International Conferences, Workshops and Meeting hosted and/or organized by the LNF see next chapter. R  ... 
doi:10.15161/oar.it/1449010032.49 fatcat:6qytx33favgkhk4g7m4ncauqh4

Visual Methods Towards Autonomous Underwater Manipulation

Gideon Billings, University, My
2022
datasets for training these methods has hindered progress in advancing visual methods for underwater applications.  ...  Extra-terrestrial ocean worlds like Europa offer tantalizing targets in the search for extant life beyond the confines of Earth's atmosphere.  ...  Blair Thornton for graciously sharing his underwater camera housing design, which was used in our work described here.  ... 
doi:10.7302/4574 fatcat:drmuvgk3pzb37dowckztgaiapu