Search results for "Python"

showing 10 items of 160 documents

Rekurento neironu tīklu novērtēšanas sistēma

2021

Darba “Rekurento neironu tīklu novērtēšanas sistēma” ietvaros tika izstrādāta sistēma, kurā var uztrenēt rekurento neironu tīklu arhitektūras uz dažādiem uzdevumiem, tām automātiski piemeklējot optimālos tīkla parametrus, un pārbaudīt uz tiem sasniegtos rezultātus, ar mērķi objektīvi novērtēt konkrēta rekurentā neironu tīkla efektivitāti. Sistēmu ir paredzēts lietot dziļās mašīnmācīšanās pētniecībā, jaunu rekurento neironu tīklu izstrādē un testēšanā, lai noteiktu vai jaunizveidotie neironu tīkli ir labāki par jau eksistējošajiem uz konkrētiem uzdevumiem.

TensorFlowDatorzinātnerekurentais neironu tīklsdziļā mašīnmācīšanāsPython
researchProduct

Movie Script Similarity Using Multilayer Network Portrait Divergence

2020

International audience; This paper addresses the question of movie similarity through multilayer graph similarity measures. Recent work has shown how to construct multilayer networks using movie scripts, and how they capture different aspects of the stories. Based on this modeling, we propose to rely on the multilayer structure and compute different similarities, so we may compare movies, not from their visual content, summary, or actors, but actually from their own storyboard. We propose to do so using “portrait divergence”, which has been recently introduced to compute graph distances from summarizing graph characteristics. We illustrate our approach on the series of six Star Wars movies.

Theoretical computer scienceComputer science02 engineering and technologyStar (graph theory)[INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]computer.software_genre01 natural sciences010305 fluids & plasmas[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]Similarity (network science)[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG]0103 physical sciences0202 electrical engineering electronic engineering information engineering[INFO]Computer Science [cs]StoryboardDivergence (statistics)Structure (mathematical logic)Network portraitMoviesMultilayer networksNetwork similarity[INFO.INFO-MM]Computer Science [cs]/Multimedia [cs.MM]Construct (python library)Scripting languageGraph (abstract data type)020201 artificial intelligence & image processingcomputer[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
researchProduct

Canonical Retina-to-Cortex Vision Model Ready for Automatic Differentiation

2020

Canonical vision models of the retina-to-V1 cortex pathway consist of cascades of several Linear+Nonlinear layers. In this setting, parameter tuning is the key to obtain a sensible behavior when putting all these multiple layers to work together. Conventional tuning of these neural models very much depends on the explicit computation of the derivatives of the response with regard to the parameters. And, in general, this is not an easy task. Automatic differentiation is a tool developed by the deep learning community to solve similar problems without the need of explicit computation of the analytic derivatives. Therefore, implementations of canonical visual neuroscience models that are ready…

Theoretical computer scienceComputer scienceAutomatic differentiationbusiness.industryComputationDeep learningPython (programming language)Task (project management)Nonlinear systemDistortionKey (cryptography)Artificial intelligencebusinesscomputercomputer.programming_language
researchProduct

Psi4: an open-source ab initio electronic structure program

2011

The Psi4 program is a new approach to modern quantum chemistry, encompassing Hartree–Fock and density-functional theory to configuration interaction and coupled cluster. The program is written entirely in C++ and relies on a new infrastructure that has been designed to permit high-efficiency computations of both standard and emerging electronic structure methods on conventional and high-performance parallel computer architectures. Psi4 offers flexible user input built on the Python scripting language that enables both new and experienced users to make full use of the program's capabilities, and even to implement new functionality with moderate effort. To maximize its impact and usefulness, …

Theoretical computer scienceComputer scienceProgramming languageComputationAb initioElectronic structureConfiguration interactionPython (programming language)computer.software_genreBiochemistryComputer Science ApplicationsComputational MathematicsCoupled clusterScripting languageMaterials ChemistryPhysical and Theoretical ChemistrycomputerLicensecomputer.programming_languageWiley Interdisciplinary Reviews: Computational Molecular Science
researchProduct

A Lightweight Network Discovery Algorithm for Resource-constrained IoT Devices

2019

Although quite simple, existing protocols for the IoT suffer from the inflexibility of centralized infrastructures and require several configuration stages. The implementation of these protocols is often prohibitive on resource-constrained devices. In this work, we propose a distributed lightweight implementation of network discovery for simple IoT devices. Our approach is based on the exchange of symbolic executable code among nodes. Based on this abstraction, we propose an algorithm that makes even IoT resource-constrained nodes able to construct the network topology graph incrementally and without any a priori information about device positioning and presence. The minimal set of executab…

Topology constructionSIMPLE (military communications protocol)Computer scienceExecutable code exchangeResource-constrained devicecomputer.file_formatConstruct (python library)Network topologyDistributed processingSet (abstract data type)Computer Networks and CommunicationHardware and ArchitectureA priori and a posterioriGraph (abstract data type)Symbolic processingExecutableInternet of ThingAlgorithmcomputerSoftwareAbstraction (linguistics)2019 International Conference on Computing, Networking and Communications (ICNC)
researchProduct

Pacientu komentāru nolūka noteikšana izmantojot mašīnmācīšanos

2020

Bakalaura darba mērķis ir automatizēt procesu aptauju atvērtā tipa jautājumu nolūka noteikšanai, izmantojot uzraudzīto mašīnmācīšanos, kā arī pierādīt izvēlētā risinājuma veiktspēju. Programmatūras risinājums paredzēts pacientu komentāru nolūka noteikšanai. Bakalaura darbs sastāv no vārdnīcas, ievada, mašīnmācīšanās teorijas, eksistējošiem risinājumiem, mašīnmācīšanās bibliotēku analīzi, datu apstrādes, modeļa parametru izklāsta, modeļa izstrādes, rezultātiem, secinājumiem, izmantotās literatūras un pielikumiem. Bakalaura darbā aprakstītas mašīnmācīšanās bibliotēkas, ko iespējams izmantot risinājuma izstrādei. Ar konkrētu izvelētu mašīnmācīšanās bibliotēku aprakstīta mašīnmācīšanās modeļa i…

Uzraudzītā mācīšanāsDatorzinātneMašinmācīšanāsmašīnmācīšanās modelismašīnmācīšanās bibliotēkasPython
researchProduct

Hyperbolic knots and cyclic branched covers

2021

International audience; We collect several results on the determination of hyperbolic knots by means of their cyclic branched covers. We construct examples of knots having two common cyclic branched covers. Finally, we brie y discuss the problem of determination of hyperbolic links

[ MATH.MATH-GT ] Mathematics [math]/Geometric Topology [math.GT]Pure mathematicsGeneral Mathematics010102 general mathematicsConstruct (python library)Mathematics::Geometric Topology01 natural sciences[MATH.MATH-GT]Mathematics [math]/Geometric Topology [math.GT]0103 physical sciences010307 mathematical physics0101 mathematicsAlgorithm[MATH.MATH-GT] Mathematics [math]/Geometric Topology [math.GT]MathematicsPublicacions Matemàtiques
researchProduct

Study of the urban dynamics by a new computer application, OH-FET

2014

International audience; The study of the urban fabric and the spatial dynamics of urban space is based on an understanding of the city as a complex system composed of individual historical objects. The OH_FET model which we developed since 2004, is based on this approach of urban space. It describes the historical urban object as the Cartesian product of three basic dimensions: function (social use), space and time from the works of Donna Peuquet in geomatics and James Allen in artificial intelligence. Although the heuristic potential of the model have already been proven to work on the cities of Tours and , more recently, Vendome in France, the integration constraints, the designing and da…

[SHS.GEO] Humanities and Social Sciences/Geography[ SHS ] Humanities and Social Sciences[SHS.GEO]Humanities and Social Sciences/Geographytemporal dimensionchronographie[SHS] Humanities and Social SciencesPython languageUrban transformation[ SHS.GEO ] Humanities and Social Sciences/Geography[SHS]Humanities and Social Sciences
researchProduct

Stimulētās mašīnmācīšanās satvars aģentiem ar atmiņu

2019

Darbā tiek aprakstīts satvars stimulētās mašīnmācīšanās algoritmu izveidei un trenēšanai. Darba ietvaros izstrādātajā satvarā iekļauti rīki, kuri paredzēti stimulētās mašīnmācīšanās aģentu atmiņas testēšanai. Izveidotas jauna tipa vides atmiņas izmantošanas spējas testēšanai un radīti stimulētās mašīnmācīšanās algoritmi ar spēju izmantot atmiņu. Satvars paredzēts lietošanai pētniecībā stimulētās mašīnmācīšanās algoritmu izstrādei un testēšanai.

atmiņaTensorFlowDatorzinātnesatvarsstimulētā mašīnmācīšanāsPython
researchProduct

Aviācijas drošības pārbaudes kontrolpunkta darbības plānošanas optimizācija

2021

Darba mērķis ir piedāvāt labāku prognozēšanas metodi aviācijas drošības pārbaudes kontrolpunktam, kas ļautu veidot un plānot precīzākus kontrolpunkta pārbaudes līniju darba grafikus. Precīzāki darba grafiki ļautu samazināt rindā gaidīšanas laiku, un ļautu pasažieriem ātrāk iziet drošības pārbaudi, bet no uzņēmējdarbības puses netiktu atvērtas pārāk daudz drošības pārbaudes līnijas, tādējādi izmantojot personāla resursu jaudu pilnībā. Tika izmantotas trīs datu kopas – izpildīto reisu datu tabula, pasažieru skenētās iekāpšanas kartes, dati par gaisa kuģu tipiem un to kapacitāti. Darbā ir aprakstīta šo datu kopu detalizēta priekšapstrāde. Plaši pielietojot dažādus vaicājumus tika iegūti jauni …

aviācijas pasažieriDatorzinātnelaika rindu prognozēšanaHolt-winters`s sezonālā izlīdzināšanas metodePython programmēšanas valoda
researchProduct