Direkt zur Hauptnavigation springen Direkt zum Inhalt springen
info(at)avldigital.remove-this.de
Deutsch English
Letzte Suchanfragen

Ergebnisse für *

Zeige Ergebnisse 1 bis 5 von 5.

  1. Transfer learning for business cycle identification
    Autor*in: Chauvet, Marcelle; Guimarães, Rafael Rockenbach da Silva
    Erschienen: [2021]
    Verlag:  Banco Central do Brasil, Brasília, DF, Brazil

    Zugang:
    Verlag (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    Keine Rechte
    Fernleihe:
    keine Fernleihe
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Schriftenreihe: Working paper series / Banco Central do Brasil ; 545 (February 2021)
    Schlagworte: neural networks; business cycle; transfer learning; deep learning
    Umfang: 1 Online-Ressource (circa 26 Seiten), Illustrationen
  2. Visual listening in: extracting brand image portrayed on social media
    Autor*in: Liu, Liu; Dzyabura, Daria; Mizik, Natalie
    Erschienen: August 2019
    Verlag:  CEFIR, Moscow

    Zugang:
    Verlag (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    VS 474
    Fernleihe:
    keine Fernleihe
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Schriftenreihe: NES working paper series ; no. 258
    Schlagworte: social media; visual marketing; brand perceptions; computervision; machine learning; deep learning; transfer learning; big data
    Umfang: 1 Online-Ressource (circa 47 Seiten), Illustrationen
  3. Model-based graph reinforcement learning for inductive traffic signal control
    Autor*in: Devailly, François-Xavier; Larocque, Denis; Charlin, Laurent
    Erschienen: [2022]
    Verlag:  GERAD, HÉC Montréal, Montréal (Québec), Canada

    Zugang:
    Verlag (kostenfrei)
    Verlag (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Signatur:
    ZSS 29
    Fernleihe:
    keine Fernleihe
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Schriftenreihe: Les cahiers du GERAD ; G-2022, 39 (September 2022)
    Schlagworte: Adaptive traffic signal control; transfer learning; multi-agent reinforcement learning; joint action modeling; model-based reinforcement learning; graph neural networks
    Umfang: 1 Online-Ressource (circa 21 Seiten), Illustrationen
  4. The Causal Effect of Attention and Recognition on the Nature of User-Generated Content
    Experimental Results from an Image-Sharing Social Network
    Autor*in: Huang, Justin T.; Kaul, Rupali; Narayanan, Sridhar
    Erschienen: 2022
    Verlag:  SSRN, [S.l.]

    Social networks rely on sharing engaging content for their users. Since continued production of user-generated content is critical to their success, they have constructed a variety of tools to motivate new content creation, to facilitate user... mehr

    Zugang:
    Verlag (kostenfrei)
    Resolving-System (kostenfrei)

    Standort:
    ZBW - Leibniz-Informationszentrum Wirtschaft, Standort Kiel
    Fernleihe:
    keine Fernleihe

     

    Social networks rely on sharing engaging content for their users. Since continued production of user-generated content is critical to their success, they have constructed a variety of tools to motivate new content creation, to facilitate user discovery of new content, and to provide attention and recognition to the best user-generated content. Past research shows that such attention and recognition increases the volume of content shared on the networks. But how do these affect the nature of content shared on their platforms? Do they cause creators to share content similar to the ones that received attention and recognition? Or do creators take risks and create different content than the ones recognized? These are the questions we ask in this paper. Our empirical context is an image-sharing social network, where creators share digital art and photography. We leverage a randomized controlled experiment to induce exogenous variation in attention and recognition to specific content. Using a transfer learning-based machine learning algorithm we convert complex images into lower-level features. This allows us to analyze similarities and differences between images. Our main findings are that creators produce and share different content on the social network, than the ones that received attention and recognition. This result is robust to a variety of ways in which we classify image content. Our results illustrate the importance of tools aimed to induce attention and recognition to the creation and development of diverse content by social media creators, and give insights into factors that motivate content creators to create content

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: Verbundkataloge
    Sprache: Englisch
    Medientyp: Buch (Monographie)
    Format: Online
    Weitere Identifier:
    Schriftenreihe: Stanford University Graduate School of Business Research Paper
    Schlagworte: User-generated content; machine learning; transfer learning; image recognition; field experiments; award recognition; attention
    Umfang: 1 Online-Ressource (37 p)
    Bemerkung(en):

    Nach Informationen von SSRN wurde die ursprüngliche Fassung des Dokuments July 2022 erstellt
  5. Region-of-Interest Based Transfer Learning Assisted Framework for Skin Cancer Detection
    Autor*in: Rehan Ashraf; Sitara Afzal; Attiq Ur Rehman; Sarah Gul; Junaid Baber; Maheen Bakhtyar; Irfan Mehmood; Oh-Young Song; Muazzam Maqsood
    Erschienen: 2020
    Verlag:  IEEE

    Melanoma is considered the most serious type of skin cancer. All over the world, the mortality rate is much high for melanoma in contrast with other cancer. There are various computer-aided solutions proposed to correctly identify melanoma cancer.... mehr

     

    Melanoma is considered the most serious type of skin cancer. All over the world, the mortality rate is much high for melanoma in contrast with other cancer. There are various computer-aided solutions proposed to correctly identify melanoma cancer. However, the difficult visual appearance of the nevus makes it very difficult to design a reliable Computer-Aided Diagnosis (CAD) system for accurate melanoma detection. Existing systems either uses traditional machine learning models and focus on handpicked suitable features or uses deep learning-based methods that use complete images for feature learning. The automatic and most discriminative feature extraction for skin cancer remains an important research problem that can further be used to better deep learning training. Furthermore, the availability of the limited available images also creates a problem for deep learning models. From this line of research, we propose an intelligent Region of Interest (ROI) based system to identify and discriminate melanoma with nevus cancer by using the transfer learning approach. An improved k-mean algorithm is used to extract ROIs from the images. These ROI based approach helps to identify discriminative features as the images containing only melanoma cells are used to train system. We further use a Convolutional Neural Network (CNN) based transfer learning model with data augmentation for ROI images of DermIS and DermQuest datasets. The proposed system gives 97.9% and 97.4% accuracy for DermIS and DermQuest respectively. The proposed ROI based transfer learning approach outperforms existing methods that use complete images for classification.

     
    Export in Literaturverwaltung   RIS-Format
      BibTeX-Format
    Quelle: BASE Fachausschnitt AVL
    Sprache: Englisch
    Medientyp: Aufsatz aus einer Zeitschrift
    Format: Online
    Übergeordneter Titel: IEEE Access, Vol 8, Pp 147858-147871 (2020)
    Schlagworte: Melanoma detection; skin cancer detection; ROI; CNN; transfer learning; Electrical engineering. Electronics. Nuclear engineering