Sökning: "transfer"

Visar resultat 1 - 5 av 3229 uppsatser innehållade ordet transfer.

  1. 1. Cross Continental Access of Information and the Boarder Gateway Protocol

    M1-uppsats, Linköpings universitet/Databas och informationsteknik

    Författare :Johan Frisk; [2019]
    Nyckelord :BGP; Boarder gateway protocol;

    Sammanfattning : The usage of technical equipment and the interconnection of all these devices has become essential to our every day life and to provide as good service as possible for the internet of today. However, many have the opportunity to inspect the data as it is being rushed across the globe to provide users with information at the press of a button. LÄS MER

  3. 2. Domain similarity metrics for predicting transfer learning performance

    Master-uppsats, Linköpings universitet/Interaktiva och kognitiva system

    Författare :Jesper Bäck; [2019]
    Nyckelord :nlp.natural language processing; machine learning; transfer learning; similarity metrics; similarity; predict; performance;

    Sammanfattning : The lack of training data is a common problem in machine learning. One solution to thisproblem is to use transfer learning to remove or reduce the requirement of training data.Selecting datasets for transfer learning can be difficult however. LÄS MER

  4. 3. Artificial Intelligence: The implications of current technological developments for Harry Collins epistemological theory and his critique of the possibilities of a general AI.

    Magister-uppsats, Göteborgs universitet/Institutionen för filosofi, lingvistik och vetenskapsteori

    Författare :Marita Isaksson; [2018-10-29]
    Nyckelord :Harry Collins; artificial intelligence; epistemology;

    Sammanfattning : Social constructivism and Harry Collins epistemological theory put focus on the sociology ofscientific knowledge, scientific practice and the nature of expertise. From his theory, inspired byLudwig Wittgenstein’s ‘forms of life’ and David Bloor’s strong programme, Collins has from thenineties until today argued against the possibilities of creating a general artificial intelligence, whichcan be compared with any cognitive functions that a human accommodates. LÄS MER

  5. 4. Exploit Unlabeled Data with Language Model for Text Classification. Comparison of four unsupervised learning models

    Master-uppsats, Göteborgs universitet/Institutionen för filosofi, lingvistikoch vetenskapsteori

    Författare :Sung-Min Yang; [2018-10-29]
    Nyckelord :Text classification; Semi-supervised learning; Unsupervised learning; Transfer learning; Natural Language Processing;

    Sammanfattning : Within a situation where Semi-Supervised Learning (SSL) is available to exploit unlabeled data, this paper shows that Language Model (LM) outperforms the three models in text classification, which three models are based on Term-Frequency Inverse Document Frequency (Tf-idf) and two pre-trained word vectors. The experimental results show that the LM outperforms the other three unsupervised learning models whether the task is easy or difficult, which the difficult task consists of imbalanced data. LÄS MER

  7. 5. SUBJECT-VERB AGREEMENT IN L2  LEARNER LANGUAGE    A study of compulsory school English in a Swedish context

    Kandidat-uppsats, Göteborgs universitet/Institutionen för språk och litteraturer

    Författare :Erik Johansson; [2018-10-18]
    Nyckelord :SLA; error analysis; learner language; concord;

    Sammanfattning : Abstract: learners of English produce subject-verb agreement errors in written productions. The study uses Error Analysis in order to collect, identify, describe, and finally, explain the occuring errors. LÄS MER