Search results for "Adversarial system"

showing 10 items of 12 documents

Improving Speaker-Independent Lipreading with Domain-Adversarial Training

2017

We present a Lipreading system, i.e. a speech recognition system using only visual features, which uses domain-adversarial training for speaker independence. Domain-adversarial training is integrated into the optimization of a lipreader based on a stack of feedforward and LSTM (Long Short-Term Memory) recurrent neural networks, yielding an end-to-end trainable system which only requires a very small number of frames of untranscribed target data to substantially improve the recognition accuracy on the target speaker. On pairs of different source and target speakers, we achieve a relative accuracy improvement of around 40% with only 15 to 20 seconds of untranscribed target speech data. On mul…

030507 speech-language pathology & audiology03 medical and health sciencesAdversarial systemRecurrent neural networkComputer scienceSpeech recognitionFeed forwardTraining (meteorology)0305 other medical scienceAccuracy improvementIndependence (probability theory)Domain (software engineering)Interspeech 2017
researchProduct

Thompson Sampling Guided Stochastic Searching on the Line for Non-stationary Adversarial Learning

2015

This paper reports the first known solution to the N-Door puzzle when the environment is both non-stationary and deceptive (adversarial learning). The Multi-Armed-Bandit (MAB) problem is the iconic representation of the exploration versus exploitation dilemma. In brief, a gambler repeatedly selects and play, one out of N possible slot machines or arms and either receives a reward or a penalty. The objective of the gambler is then to locate the most rewarding arm to play, while in the process maximize his winnings. In this paper we investigate a challenging variant of the MAB problem, namely the non-stationary N-Door puzzle. Here, instead of directly observing the reward, the gambler is only…

Adversarial systemComputer scienceProperty (programming)business.industryProcess (computing)Reinforcement learningArtificial intelligencebusinessRepresentation (mathematics)Bayesian inferenceMulti-armed banditThompson sampling2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA)
researchProduct

Robust consensus in social networks and coalitional games

2014

We study an n-player averaging process with dynamics subject to controls and adversarial disturbances. The model arises in two distinct application domains: i) coalitional games with transferable utilities (TU) and ii) opinion propagation. We study conditions under which the average allocations achieve robust consensus to some predefined target set.

Adversarial systemMathematical optimizationProcess (engineering)Game theory networks allocations robust receding horizon control.EconomicsSettore MAT/09 - Ricerca OperativaSet (psychology)Mathematical economicsGame theory
researchProduct

Cloning and training collective intelligence with generative adversarial networks

2021

Industry 4.0 and highly automated critical infrastructure can be seen as cyber‐physical‐social systems controlled by the Collective Intelligence. Such systems are essential for the functioning of the society and economy. On one hand, they have flexible infrastructure of heterogeneous systems and assets. On the other hand, they are social systems, which include collaborating humans and artificial decision makers. Such (human plus machine) resources must be pre‐trained to perform their mission with high efficiency. Both human and machine learning approaches must be bridged to enable such training. The importance of these systems requires the anticipation of the potential and previously unknow…

Cognitive scienceTechnological innovations. AutomationCloning (programming)Computer scienceHD45-45.2Collective intelligenceManufacturestekoälyTraining (civil)Industrial and Manufacturing EngineeringTS1-2301Computer Science ApplicationsAdversarial systemkoneoppiminenArtificial IntelligenceHardware and Architectureautomaatiojärjestelmätihminen-konejärjestelmätälytekniikkaGenerative grammarIET Collaborative Intelligent Manufacturing
researchProduct

Crowd-Averse Cyber-Physical Systems: The Paradigm of Robust Mean-Field Games

2016

For a networked controlled system, we illustrate the paradigm of robust mean-field games. This is a modeling framework at the interface of differential game theory, mathematical physics, and $H_{\infty}$ - optimal control that tries to capture the mutual influence between a crowd and its individuals. First, we establish a mean-field system for such games including the effects of adversarial disturbances. Second, we identify the optimal response of the individuals for a given population behavior. Third, we provide an analysis of equilibria and their stability.

Computer Science::Computer Science and Game Theory0209 industrial biotechnologyTheoretical computer scienceComputer scienceInterface (computing)PopulationStability (learning theory)02 engineering and technology01 natural sciencesAdversarial system020901 industrial engineering & automationSettore ING-INF/04 - AutomaticaControl theoryRobustness (computer science)Differential game0101 mathematicsElectrical and Electronic Engineeringcrowd-averse cyber-physical systems robust mean-field games paradigm networked control system differential game theory mathematical physics H∞-optimal control mean-field system adversarial disturbance effecteducationeducation.field_of_studyCyber-physical systemOptimal controlComputer Science Applications010101 applied mathematicsControl and Systems EngineeringSettore MAT/09 - Ricerca OperativaIEEE Transactions on Automatic Control
researchProduct

Countering Adversarial Inference Evasion Attacks Towards ML-Based Smart Lock in Cyber-Physical System Context

2021

Machine Learning (ML) has been taking significant evolutionary steps and provided sophisticated means in developing novel and smart, up-to-date applications. However, the development has also brought new types of hazards into the daylight that can have even destructive consequences required to be addressed. Evasion attacks are among the most utilized attacks that can be generated in adversarial settings during the system operation. In assumption, ML environment is benign, but in reality, perpetrators may exploit vulnerabilities to conduct these gradient-free or gradient-based malicious adversarial inference attacks towards cyber-physical systems (CPS), such as smart buildings. Evasion attac…

ExploitComputer sciencebusiness.industryCyber-physical systemevasion attacksEvasion (network security)Context (language use)Adversarial machine learningComputer securitycomputer.software_genreadversarial machine learningdefensive mechanismscyber-physical systemAdversarial systemSmart lockkoneoppiminenälytekniikkabusinesskyberturvallisuuscomputerverkkohyökkäyksetBuilding automation
researchProduct

Generating Hyperspectral Skin Cancer Imagery using Generative Adversarial Neural Network

2020

In this study we develop a proof of concept of using generative adversarial neural networks in hyperspectral skin cancer imagery production. Generative adversarial neural network is a neural network, where two neural networks compete. The generator tries to produce data that is similar to the measured data, and the discriminator tries to correctly classify the data as fake or real. This is a reinforcement learning model, where both models get reinforcement based on their performance. In the training of the discriminator we use data measured from skin cancer patients. The aim for the study is to develop a generator for augmenting hyperspectral skin cancer imagery. peerReviewed

Imagery PsychotherapySkin NeoplasmsComputer science0211 other engineering and technologiesComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologygenerative adversarial neural networksneuroverkotMachine learningcomputer.software_genre030218 nuclear medicine & medical imagingMachine Learningihosyöpä03 medical and health sciencesAdversarial system0302 clinical medicineHumansLearningReinforcement learning021101 geological & geomatics engineeringArtificial neural networkskin cancerbusiness.industryspektrikuvausHyperspectral imagingComputingMethodologies_PATTERNRECOGNITIONkuvantaminenNeural Networks ComputerArtificial intelligencebusinesscomputerGenerative grammarGenerator (mathematics)
researchProduct

The two faces of Nordic management? Nordic firms and their employee relations in the Baltic States

2009

This study examines Nordic management styles in union and non-union industrial enterprises in the Baltic States (Estonia, Latvia, Lithuania) through case studies of nine Nordic subsidiary companies, based on on-site interviews with management and employees.1 This analysis construes the ‘Nordic model’ of management style as ‘bargained constitutional’ or ‘sophisticated consultative’, following Purcell and Ahlstrand's (1994) matrix of management styles in the highly unionized countries of origin, characterized as coordinated market economies. The case studies reveal that in the Baltic liberal-market environment, Nordic employers exhibit a variety of management styles, ranging from sophisticate…

Organizational Behavior and Human Resource ManagementStrategy and ManagementSubsidiaryManagement stylesConstitutionalismPaternalismAdversarial systemEconomyManagement of Technology and InnovationPolitical scienceIndustrial relationsTrade unionBusiness and International ManagementNordic modelIndustrial relationsThe International Journal of Human Resource Management
researchProduct

The defendant’s guilt beyond a reasonable doubt in the Italian criminal justice system

2021

The criminal law standard of Beyond A Reasonable Doubt (BARD) constitutes an evidentiary and judicial rule, formulated and applied for centuries in common law jurisdictions, which was expressly stated in the Italian Code of Criminal Procedure only about fifteen years ago. Unfortunately, the concept of reasonable doubt is inherently complex and does not easily lend itself to definition or refinement. In this regard, the Author examines especially the various positions and elaborations developed by legal literature and case-law in Italy, proposing a specific interpretation of the BARD rule that enhances and completes the particular procedural connotations of the adversarial system adopted i…

Sociology and Political ScienceCommon lawO standard penal do Beyond A Reasonable Doubt (BARD) constitui uma regra de prova e de juízo formulada e aplicada durante séculos em jurisdições de common law que foi expressamente introduzida no Código de Processo Penal italiano apenas cerca de quinze anos atrás. Infelizmente o conceito dedúvida razoável é inerentemente complexo e não se presta facilmente a uma definição ou a uma melhor delimitação. Diante disso o autor examina sobretudo as diferentes posições e elaborações desenvolvidas pela doutrina e pela jurisprudência na Itália oferecendo uma interpretação específica da regra BARD que valoriza e completa as conotações processuais particulares do sistema acusatório adotado na justiça penal italiana.Criminal procedureAdversarial systemreasonable doubtPolitical sciencefair trial.criminal procedureReasonable doubtPresumption of innocenceInterpretation (philosophy)dúvida razoável; processo penal; presunção de inocência; ônus da prova; standard de pro-va; método de raciocínio judicial; justo processo.judicial reasoning methodKPsychiatry and Mental healthreasonable doubt; criminal procedure; presumption of innocence; burden of proof; stand-ard of proof; judicial reasoning method; fair trial.AnthropologyLawSettore IUS/16 - Diritto Processuale PenaleCriminal lawpresumption of innocencestand-ard of proofburden of proofLawSafety ResearchSettore IUS/17 - Diritto PenaleCriminal justice
researchProduct

Groups' warmth is a personal matter: Understanding consensus on stereotype dimensions reconciles adversarial models of social evaluation

2020

Abstract As proponents of two theories of social evaluation, we disagree whether people spontaneously differentiate societal groups' conservative-progressive beliefs (distinct claim of the agency-beliefs-communion or ABC model) or warmth/communion (distinct claim of the stereotype content model or SCM). Our adversarial collaboration provides one way to resolve this debate. Examining people from four continents who differentiated groups in their country (N = 2356), we found lower consensus on groups' warmth/communion compared to agency/~competence and beliefs (Studies 1–4). Consensus on groups' warmth/communion was lower because people differed in self-rated agency and beliefs, and they infe…

Sociology and Political ScienceSocial PsychologySelfmedia_common.quotation_subject05 social sciencesAgency (philosophy)050109 social psychologyStereotypeStereotype content model050105 experimental psychologyAdversarial systemSimilarity (psychology)0501 psychology and cognitive sciencesPsychologyAdversarial collaborationSocial psychologySocial evaluationmedia_commonJournal of Experimental Social Psychology
researchProduct