From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning
Autor: | Tomislav Lipic, Ilona M. Kulikovskikh, Tomislav Šmuc |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2020 |
Předmět: |
item information
Computer science General Physics and Astronomy lcsh:Astrophysics 02 engineering and technology Machine learning computer.software_genre Article active learning lcsh:QB460-466 Item response theory multiple-choice testing 0202 electrical engineering electronic engineering information engineering Entropy (information theory) lcsh:Science pool-based sampling item response theory deep learning business.industry Deep learning 05 social sciences 050301 education lcsh:QC1-999 Data set Information function lcsh:Q 020201 artificial intelligence & image processing Knowledge transmission Artificial intelligence business 0503 education computer lcsh:Physics Electrical Engineering Active learning environment |
Zdroj: | Entropy (Basel. Online) Entropy Volume 22 Issue 8 Entropy, Vol 22, Iss 906, p 906 (2020) |
Popis: | 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&rsquo knowledge, while machine active learning strategies lack versatile tools for shifting the focus of instruction away from knowledge transmission to learners&rsquo 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&mdash 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. |
Databáze: | OpenAIRE |
Externí odkaz: |