From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning
Machines usually employ a guess-and-check strategy to analyze data: they take the data, make a guess, check the answer, adjust it with regard to the correct one if necessary, and try again on a new data set. An active learning environment guarantees better performance while training on less, but car...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/22/8/906 |
| _version_ | 1797557345937522688 |
|---|---|
| author | Ilona Kulikovskikh Tomislav Lipic Tomislav Šmuc |
| author_facet | Ilona Kulikovskikh Tomislav Lipic Tomislav Šmuc |
| author_sort | Ilona Kulikovskikh |
| collection | DOAJ |
| description | Machines usually employ a guess-and-check strategy to analyze data: they take the data, make a guess, check the answer, adjust it with regard to the correct one if necessary, and try again on a new data set. An active learning environment guarantees better performance while training on less, but carefully chosen, data which reduces the costs of both annotating and analyzing large data sets. This issue becomes even more critical for deep learning applications. Human-like active learning integrates a variety of strategies and instructional models chosen by a teacher to contribute to learners’ knowledge, while machine active learning strategies lack versatile tools for shifting the focus of instruction away from knowledge transmission to learners’ knowledge construction. We approach this gap by considering an active learning environment in an educational setting. We propose a new strategy that measures the information capacity of data using the information function from the four-parameter logistic item response theory (4PL IRT). We compared the proposed strategy with the most common active learning strategies—Least Confidence and Entropy Sampling. The results of computational experiments showed that the Information Capacity strategy shares similar behavior but provides a more flexible framework for building transparent knowledge models in deep learning. |
| first_indexed | 2024-03-10T17:15:51Z |
| format | Article |
| id | doaj.art-fce34e0862aa46b192b289912828f247 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T17:15:51Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-fce34e0862aa46b192b289912828f2472023-11-20T10:31:54ZengMDPI AGEntropy1099-43002020-08-0122890610.3390/e22080906From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active LearningIlona Kulikovskikh0Tomislav Lipic1Tomislav Šmuc2Department of Information Systems and Technologies, Samara National Research University, Moskovskoe Shosse 34, 443086 Samara, RussiaDivision of Electronics, Ruđer Bošković Institute, Bijenička cesta 54, 10000 Zagreb, CroatiaDivision of Electronics, Ruđer Bošković Institute, Bijenička cesta 54, 10000 Zagreb, CroatiaMachines usually employ a guess-and-check strategy to analyze data: they take the data, make a guess, check the answer, adjust it with regard to the correct one if necessary, and try again on a new data set. An active learning environment guarantees better performance while training on less, but carefully chosen, data which reduces the costs of both annotating and analyzing large data sets. This issue becomes even more critical for deep learning applications. Human-like active learning integrates a variety of strategies and instructional models chosen by a teacher to contribute to learners’ knowledge, while machine active learning strategies lack versatile tools for shifting the focus of instruction away from knowledge transmission to learners’ knowledge construction. We approach this gap by considering an active learning environment in an educational setting. We propose a new strategy that measures the information capacity of data using the information function from the four-parameter logistic item response theory (4PL IRT). We compared the proposed strategy with the most common active learning strategies—Least Confidence and Entropy Sampling. The results of computational experiments showed that the Information Capacity strategy shares similar behavior but provides a more flexible framework for building transparent knowledge models in deep learning.https://www.mdpi.com/1099-4300/22/8/906item informationpool-based samplingmultiple-choice testingitem response theoryactive learningdeep learning |
| spellingShingle | Ilona Kulikovskikh Tomislav Lipic Tomislav Šmuc From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning Entropy item information pool-based sampling multiple-choice testing item response theory active learning deep learning |
| title | From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning |
| title_full | From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning |
| title_fullStr | From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning |
| title_full_unstemmed | From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning |
| title_short | From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning |
| title_sort | from knowledge transmission to knowledge construction a step towards human like active learning |
| topic | item information pool-based sampling multiple-choice testing item response theory active learning deep learning |
| url | https://www.mdpi.com/1099-4300/22/8/906 |
| work_keys_str_mv | AT ilonakulikovskikh fromknowledgetransmissiontoknowledgeconstructionasteptowardshumanlikeactivelearning AT tomislavlipic fromknowledgetransmissiontoknowledgeconstructionasteptowardshumanlikeactivelearning AT tomislavsmuc fromknowledgetransmissiontoknowledgeconstructionasteptowardshumanlikeactivelearning |