Solving Hofstadter’s Analogies Using Structural Information Theory
| Authors |
|
|---|---|
| Publication date | 2021 |
| Host editors |
|
| Book title | Artificial Intelligence and Machine Learning |
| Book subtitle | 32nd Benelux Conference, BNAIC/Benelearn 2020, Leiden, The Netherlands, November 19–20, 2020 : revised selected papers |
| ISBN |
|
| ISBN (electronic) |
|
| Series | Communications in Computer and Information Science |
| Event | 32nd Benelux Conference on Artificial Intelligence and Belgian-Dutch Conference on Machine Learning, BNAIC/Benelearn 2020 |
| Pages (from-to) | 106-121 |
| Number of pages | 16 |
| Publisher | Cham: Springer |
| Organisations |
|
| Abstract |
Analogies are common part of human life; our ability to handle them is critical in problem solving, humor, metaphors and argumentation. This paper introduces a method to solve string-based (symbolic) analogies based on hybrid inferential process integrating Structural Information Theory—a framework used to predict phenomena of perceptual organization—with some metric-based processing. Results are discussed against two empirical experiments, one of which conducted along this work, together with the development of a Python version of the SIT encoding algorithm PISA. |
| Document type | Conference contribution |
| Language | English |
| Published at | https://doi.org/10.1007/978-3-030-76640-5_7 |
| Other links | https://www.scopus.com/pages/publications/85111324885 |
| Downloads |
Rijsdijk-Sileno2021_Chapter_SolvingHofstadterSAnalogiesUsi
(Final published version)
|
| Permalink to this page | |
