64 Hits in 4.5 sec

NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation [article]

Anastasis Kratsios, Cody Hyndman
2021 arXiv   pre-print
We show that NEU can learn any feature map with these two properties if that feature map is asymptotically deformable into the identity.  ...  This paper introduces a meta-procedure, called Non-Euclidean Upgrading (NEU), which learns feature maps that are expressive enough to embed the universal approximation property (UAP) into most model classes  ...  The authors thank Alina Stancu (Concordia University) for helpful discussions, Josef Teichmann and the entire working group at ETH for their helpful feedback, and Behnoosh Zamanlooy for the Python guidance  ... 
arXiv:1809.00082v4 fatcat:5ue5d7svp5dyhedo7er65ou7cm

An Artificial Neural Network Model to Forecast Exchange Rates

Vincenzo Pacelli, Vitoantonio Bevilacqua, Michele Azzollini
2011 Journal of Intelligent Learning Systems and Applications  
For the purposes of this research, the optimal MLP neural network topology has been designed and tested by means the specific genetic algorithm multi-objective Pareto-Based.  ...  The objective of the research is to predict the trend of the exchange rate Euro/USD up to three days ahead of last data available.  ...  Acknowledgements The authors acknowledge to the anonymous referees for their thoughtful and constructive suggestions and Maria Rosaria Di Muro for the valuable support.  ... 
doi:10.4236/jilsa.2011.32008 fatcat:rvc5qhoe2red5pfvsir2veaueq

Smoothing Policies and Safe Policy Gradients [article]

Matteo Papini, Matteo Pirotta, Marcello Restelli
2022 arXiv   pre-print
Policy Gradient (PG) algorithms are among the best candidates for the much-anticipated applications of reinforcement learning to real-world control tasks, such as robotics.  ...  Through a joint, adaptive selection of these meta-parameters, we obtain a policy gradient algorithm with monotonic improvement guarantees.  ...  The authors would like to thank Gergely Neu for his suggestions on how to improve the Safe Policy Gradient algorithm and its theoretical analysis.  ... 
arXiv:1905.03231v2 fatcat:42eel7ra2rb2bft4nlid7nl26y

Algorithms for Reinforcement Learning

Csaba Szepesvári
2010 Synthesis Lectures on Artificial Intelligence and Machine Learning  
The goal in reinforcement learning is to develop efficient learning algorithms, as well as to understand the algorithms' merits and limitations.  ...  Reinforcement learning is of great interest because of the large number of practical applications that it can be used to address, ranging from problems in artificial intelligence to operations research  ...  (Shapiro, 2003) such as PEGASUS (Ng and Jordan, 2000) , online learning in MDPs with arbitrary reward processes (Even-Dar et al., 2005; Neu et al., 2010) , or learning with (almost) no restrictions  ... 
doi:10.2200/s00268ed1v01y201005aim009 fatcat:bdkpvafw4net5npq5tbtq7jeci

Introduction to Online Convex Optimization [article]

Elad Hazan
2021 arXiv   pre-print
In many practical applications the environment is so complex that it is infeasible to lay out a comprehensive theoretical model and use classical algorithmic theory and mathematical optimization.  ...  It is necessary as well as beneficial to take a robust approach, by applying an optimization method that learns as one goes along, learning from experience as more aspects of the problem are observed.  ...  I am very thankful to Wouter Koolen-Wijkstra for a helpful suggestion in the analysis of the Online Newton Step algorithm.  ... 
arXiv:1909.05207v2 fatcat:2fvtye3uo5dajjy4hfdwk33lbq

Entity Retrieval and Text Mining for Online Reputation Monitoring [article]

Pedro Saleiro
2018 arXiv   pre-print
Therefore, we address the problem of Entity-Relationship (E-R) retrieval in which the goal is to search for multiple connected entities.  ...  We argue that this format is too restrictive as end users often like to have the flexibility to search for entity-centric information that is not available in predefined charts.  ...  The framework is adaptable and can be reused in different application scenarios, such as finance and politics.  ... 
arXiv:1801.07743v1 fatcat:f56lljaavnd6zm4vnngs2m3tga

Digital Transformation in Learning Organizations [chapter]

Christian Helbig, Sandra Hofhues, Marc Egloffstein, Dirk Ifenthaler
2021 Digital Transformation of Learning Organizations  
Which design perspectives can be used for digital transformation in learning organizations?  ...  have in learning organizations.  ...  We thank all those who participated in the project, as well as the colleagues from the three regional SFIVET sites who contributed with their reflections, critics and comments to develop and define the  ... 
doi:10.1007/978-3-030-55878-9_14 fatcat:l36faznntjexxoadcstygtf6eu

Poster Presentations at the 8th Canadian Conference on Dementia (CCD), Ottawa, October 2015

Various Authors
2015 Canadian Geriatrics Journal  
Capacity building for global health issues related to dementia is necessary to bridge the generation gap in the search for global dementia solutions.  ...  We need to harness the momentum for change and impact found in the energy and innovation from younger generations. Objectives: 1.  ...  Results: In our randomized verification tests, manifold learning algorithms clearly improve the performance of the automatic diagnosis task.  ... 
doi:10.5770/cgj.18.218 fatcat:nvcz53y57rcqbgs33vwxhnn4r4

Abstracts of Working Papers in Economics

1992 Abstracts of Working Papers in Economics  
We apply a non-linear nearest neighbor algorithm to identify stochastic and deterministic patterns in the daily returns.  ...  Finally, we plead for a different analogy between politics and economics, one that fccusses on organizations, and note that this line of thought is consistent with other main trends in public choice.  ...  Learning is assumed to be endogenous to the diffusion process -firms learn only from the experience of other firms that have adopted in the past.  ... 
doi:10.1017/s0951007900002977 fatcat:ng24loz5ubcmja75vxy6nsmoja


Orkhan Hajizada Orkhan Hajizada
2021 Proceeding of The International Research Education & Training Centre  
Given the demand for energy and energy resources in modern times, we can see how important a sustainable energy policy is. Keywords: green economy, sustainable development, green policy.  ...  In recent years, the developed countries of the world are building their policies to ensure more sustainable development.  ...  application in the economic sphere will create conditions for sustainable economic development. 4.  ... 
doi:10.36962/piretc1707202116 fatcat:zkinuythufdbdilfqsmlyq5vqm

In Silico Studies Targeting G-protein Coupled Receptors for Drug Research Against Parkinson's Disease

Agostinho Lemos, Rita Melo, Antonio Jose Preto, Jose Guilherme Almeida, Irina Sousa Moreira, Maria Natalia Dias Soeiro Cordeiro
2018 Current Neuropharmacology  
The investigation for non-dopaminergic therapies has been largely explored as an attempt to counteract the motor side effects associated with dopamine replacement therapy.  ...  receptors, on the pathophysiology of PD and the importance of structure-and ligand-based in silico approaches for the development of small molecules to target these receptors.  ...  and meta positions of the phenyl ring.  ... 
doi:10.2174/1570159x16666180308161642 pmid:29521236 pmcid:PMC6080095 fatcat:ofgpbzklozdixjri7javhbekhq

Ultra-High-Energy Cosmic Rays: The Intersection of the Cosmic and Energy Frontiers [article]

A. Coleman
2022 arXiv   pre-print
The present white paper is submitted as part of the "Snowmass" process to help inform the long-term plans of the United States Department of Energy and the National Science Foundation for high-energy physics  ...  It summarizes the science questions driving the Ultra-High-Energy Cosmic-Ray (UHECR) community and provides recommendations on the strategy to answer them in the next two decades.  ...  to the original Snowmass call for submissions.  ... 
arXiv:2205.05845v3 fatcat:ixjqj3ck5rb2pibjxm53zgf664

Abstracts of Working Papers in Economics

2001 Abstracts of Working Papers in Economics  
Thus, entry by a marker maker results in uniformly higher surpluses for buyers and sellers and higher AB We examine an economy where human capital is the cause of growth.  ...  Olivella, Pau AB We analyze an industry where a dominant buyer may foreclose its rivals (with whom it competes a la Cournot in the final good market) from access to an efficient supplier of an intermediate  ...  But, in the last two decades the extent of private finance has increased in most of these countries, and private finance now accounts for around a quarter of all health care finance.  ... 
doi:10.1017/s0951007900005441 fatcat:t6dkdz4vfzcdhekrmsa2yjmjfm

From PDF to structured references: A comparative study on tools for bibliographic references extraction and parsing

Alessia Cioffi, Silvio Peroni, Fabio Vitali
2022 Zenodo  
However, in some of the subtasks investigated alongside the overall results, other tools resulted to have a better performance in specific tasks.  ...  Thus, in this variegated scenario, different solutions can be adopted on the basis on the user's requirements.  ...  For what concerns the language ease of usage, the choice was almost easy with the XML (eXtensible Markup Language) meta-language.  ... 
doi:10.5281/zenodo.6616296 fatcat:7z3kr36khfec7lbmfg4rwuam3m

Final Program, Thirty-Eighth Annual Meeting International Neuropsychological Society

2010 Journal of the International Neuropsychological Society  
Test-retest stability was high for the Response Speed factor (.95), and moderate for Learning and Memory (.67) and Variability factors (.72).  ...  Results: A three factor structure-Response Speed, Learning and Memory, and Variability (ICV) -accounted for 48.4% of the total variance. Factors had moderate covariance with each other (.43 to .70).  ...  Objective: Develop a measure of memory and learning for the NIH Toolbox that is applicable across the age span of 3 to 85, easy to use, and in the public domain.  ... 
doi:10.1017/s1355617710000226 fatcat:cvsuvca32nhnbf3f66rmxq7eiq
« Previous Showing results 1 — 15 out of 64 results