189 Hits in 10.1 sec

Navigating the maze of graph analytics frameworks using massive graph datasets

Nadathur Satish, Narayanan Sundaram, Md. Mostofa Ali Patwary, Jiwon Seo, Jongsoo Park, M. Amber Hassaan, Shubho Sengupta, Zhaoming Yin, Pradeep Dubey
2014 Proceedings of the 2014 ACM SIGMOD international conference on Management of data - SIGMOD '14  
This makes the end-users' choice of graph framework dependent not only on ease of use but also on performance.  ...  These changes will enable end-users to choose frameworks based mostly on ease of use.  ...  We consider a wider variety of frameworks and our work is more interested in answering the more general productivity-vs-performance question for graph analytics.  ... 
doi:10.1145/2588555.2610518 dblp:conf/sigmod/SatishSPSPHSYD14 fatcat:l5mcilp3ujezbliklr4h2pwrfe

Polyphorm: Structural Analysis of Cosmological Datasets via Interactive Physarum Polycephalum Visualization [article]

Oskar Elek, Joseph N. Burchett, J. Xavier Prochaska, Angus G. Forbes
2020 arXiv   pre-print
extrapolate from sparse datasets, such as galaxy maps archived in the Sloan Digital Sky Survey, and then use these extrapolations to inform analyses of a wide range of other data, such as spectroscopic  ...  We describe details of Polyphorm's simulation model and its interaction and visualization modalities, and we evaluate Polyphorm through three scientific use cases that demonstrate the effectiveness of  ...  Special thanks to Jan Ivanecký for his help in developing an initial prototype of the software.  ... 
arXiv:2009.02441v1 fatcat:qqhvdclulndklmkwyo6q564d2y

Statistical Learning of Neuronal Functional Connectivity

Chunming Zhang, Yi Chai, Xiao Guo, Muhong Gao, David Devilbiss, Zhengjun Zhang
2016 Technometrics  
An application of the proposed method to a real spike train dataset, obtained from the prelimbic region of the prefrontal cortex of adult male rats when performing a T-maze based delayed-alternation task  ...  We study the consistency of parameter estimation of the proposed method.  ...  ACKNOWLEDGMENTS The authors thank the editor, associate editor, and two anonymous referees for insightful comments. C.  ... 
doi:10.1080/00401706.2016.1142904 fatcat:hrwtwua3wrab3cphrammw5y7fm

Attention, please! A survey of Neural Attention Models in Deep Learning [article]

Alana de Santana Correia, Esther Luna Colombini
2021 arXiv   pre-print
By critically analyzing 650 works, we describe the primary uses of attention in convolutional, recurrent networks and generative models, identifying common subgroups of uses and applications.  ...  We also developed and made public an automated methodology to facilitate the development of reviews in the area.  ...  visual navigation task in random mazes.  ... 
arXiv:2103.16775v1 fatcat:lwkw42lrircorkymykpgdmlbwq

Towards Lifelong Self-Supervision: A Deep Learning Direction for Robotics [article]

Jay M. Wong
2016 arXiv   pre-print
Despite outstanding success in vision amongst other domains, many of the recent deep learning approaches have evident drawbacks for robots.  ...  This manuscript surveys recent work in the literature that pertain to applying deep learning systems to the robotics domain, either as means of estimation or as a tool to resolve motor commands directly  ...  of the author(s) and do not necessarily reflect the views of organization.  ... 
arXiv:1611.00201v1 fatcat:nqatcsrysvd7nn3ljpc4eankmq

The AtLarge Vision on the Design of Distributed Systems and Ecosystems [article]

Alexandru Iosup, Laurens Versluis, Animesh Trivedi, Erwin van Eyk, Lucian Toader, Vincent van Beek, Giulia Frascaria, Ahmed Musaafir, Sacheendra Talluri
2019 arXiv   pre-print
Toward this vision, we propose the AtLarge design framework, accompanied by a set of 8 core design principles.  ...  Threatening to slow down the stream of working designs, we identify the mounting pressure of scale and complexity of (eco-)systems, of ill-defined and wicked problems, and of unclear processes, methods  ...  Acknowledgments Work supported by the projects Vidi MagnaData and Commit.  ... 
arXiv:1902.05416v1 fatcat:2mvgfuiv7zahfno6xz7lkhmrby

The hidden architecture of higher education: building a big data infrastructure for the 'smarter university'

Ben Williamson
2018 International Journal of Educational Technology in Higher Education  
It examines the sociotechnical networks of organizations, software programs, standards, dashboards and visual analytics technologies that constitute the infrastructure, and how these technologies are fused  ...  The analysis foregrounds how HE is being reimagined through the utopian ideal of the 'smarter university' while simultaneously being reformed through the political project of marketization.  ...  Availability of data and materials Not applicable. Author information Ben Williamson is a lecturer at the University of Stirling, UK.  ... 
doi:10.1186/s41239-018-0094-1 fatcat:jsm7me5eebcgff5znwvpqhae5y

Theta phase coding in a network model of the entorhinal cortex layer II with entorhinal-hippocampal loop connections

Jun Igarashi, Hatsuo Hayashi, Katsumi Tateno
2006 Cognitive Neurodynamics  
In this talk, I will begin with the useful behavior of NMF in EEG pattern classification, which plays a critical role in noninvasive brain computer interface (BCI).  ...  To this end, we propose a neural network based retrainable framework for object recognition, which consists of four components-preprocessing, binary classification, object identification, and outlier rejection  ...  CONCLUSION We designed an element circuit for implementing PLL neural networks using the pulse-modulation approach. We verified the fundamental operation of two coupled element circuits with HSPICE.  ... 
doi:10.1007/s11571-006-9003-8 pmid:19003510 pmcid:PMC2267667 fatcat:avihqfr6a5e7tm43lythi27n3a

The BrainScaleS-2 accelerated neuromorphic system with hybrid plasticity [article]

Christian Pehle, Sebastian Billaudelle, Benjamin Cramer, Jakob Kaiser, Korbinian Schreiber, Yannik Stradmann, Johannes Weis, Aron Leibfried, Eric Müller, Johannes Schemmel
2022 arXiv   pre-print
While implementation details differ, spiking neural networks - sometimes referred to as the third generation of neural networks - are the common abstraction used to model computation with such systems.  ...  Since the beginning of information processing by electronic components, the nervous system has served as a metaphor for the organization of computational primitives.  ...  Scholze from the group "Hochparallele VLSI-Systeme und Neuromikroelektronik" of C.  ... 
arXiv:2201.11063v2 fatcat:5zniosxozzapjan3afpg6ywggi

Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns

Tânia F G G Cova, Alberto A C C Pais
2019 Frontiers in Chemistry  
In this review, the most exciting developments concerning the use of ML in a range of different chemical scenarios are described.  ...  The latter class of ML algorithms is capable of combining raw input into layers of intermediate features, enabling bench-to-bytes designs with the potential to transform several chemical domains.  ...  Further application of this tool will foster the development of frameworks based on criteria-decision analytics, optimizing the design of manufacturing processes.  ... 
doi:10.3389/fchem.2019.00809 pmid:32039134 pmcid:PMC6988795 fatcat:ld2p6272hfhovpxfmros35lism

Scientific intuitions about the mind are wrong, misled by consciousness

Leonid Perlovsky
2016 Behavioral and Brain Sciences  
Logic is a fundamental reason why computational accounts of the mind have failed. Combinatorial complexity preventing computational accounts is equivalent to the Gödelian incompleteness of logic.  ...  For this reason, intuitions of psychologists, cognitive scientists, and mathematicians modeling the mind are biased toward logic.  ...  As such, we think that one of the chief virtues of Anderson's work is that it brings us one step closer to the abandonment of massive modularity as a model of the brain.  ... 
doi:10.1017/s0140525x15001624 pmid:27562356 fatcat:4dpatuvkafgo5prtex2hf6cz2i

Amanuensis: The Programmer's Apprentice [article]

Thomas Dean, Maurice Chiang, Marcus Gomez, Nate Gruver, Yousef Hindy, Michelle Lam, Peter Lu, Sophia Sanchez, Rohun Saxena, Michael Smith, Lucy Wang, Catherine Wong
2018 arXiv   pre-print
This document provides an overview of the material covered in a course taught at Stanford in the spring quarter of 2018.  ...  The course draws upon insight from cognitive and systems neuroscience to implement hybrid connectionist and symbolic reasoning systems that leverage and extend the state of the art in machine learning  ...  The IMAGINATION MODEL is implemented as an interaction network [6] that could also be represented using the graph-networks framework.  ... 
arXiv:1807.00082v2 fatcat:piwexqa2xvgg5ec5xwkswstswy

Deep Reinforcement Learning [article]

Yuxi Li
2018 arXiv   pre-print
We start with background of artificial intelligence, machine learning, deep learning, and reinforcement learning (RL), with resources.  ...  The authors propose policy-space response oracle (PSRO), and its approximation, deep cognitive hierarchies (DCH), to compute best responses to a mixture of policies using deep RL, and to compute new meta-strategy  ...  distributions using empirical game-theoretic analysis.  ... 
arXiv:1810.06339v1 fatcat:kp7atz5pdbeqta352e6b3nmuhy

Open Source Intelligence and its Applications in Next Generation Cyber Security - A Literature Review

U. Yogish Pai, K. Krishna Prasad
2021 Zenodo  
framework and methodology for future research.  ...  Originality: A literature review have had been carried out using secondary data gathered from various online sources, and new knowledge in the form of findings was derived in order to construct a theoretical  ...  The platform consists of four key components, such as GeoData Cloud -an architecture for hoarding and managing diverse datasets, Real-time streaming data harvesting method, Data and analytics platform  ... 
doi:10.5281/zenodo.5171579 fatcat:fp6wodk45zgwtnuxsnnxjnw7oa

Reusable Component Oriented Agents: A New Architecture [chapter]

W. H. Boshoff, E. M. Ehlers
2006 Lecture Notes in Computer Science  
The use of implicit graphs requires less memory at any given time, but the time required to reevaluate the graph is increased [Hi05] .  ...  The state of the maze comprises various features which include the number of maze arms, the status of obstacles within the maze and the current location and heading of the rat.  ...  List of acronyms  ... 
doi:10.1007/11802372_71 fatcat:tvun76tbbbgwfitfoj75sazvku
« Previous Showing results 1 — 15 out of 189 results