Development of Few-Shot Learning Capabilities in Artificial Neural Networks When Learning Through Self-Supervised Interaction
Autor(en): | Clay, Viviane Pipa, Gordon Kuhnberger, Kai-Uwe Konig, Peter |
Stichwörter: | Embodied AI; enactivism; Encoding; Encoding (symbols); Encodings; fast mapping; few-shot learning; Job analysis; Mapping; Neural networks; Object recognition; Pattern analysis; Pole and tower; Poles and towers; reinforcement learning; Reinforcement learnings; representation learning; Semantics; Signal encoding; Task analysis; Training; Visualization | Erscheinungsdatum: | 2023 | Herausgeber: | IEEE Computer Society | Journal: | IEEE Transactions on Pattern Analysis and Machine Intelligence | Startseite: | 1–12 | Zusammenfassung: | Most artificial neural networks used for object recognition are trained in a fully supervised setup. This is not only resource consuming as it requires large data sets of labeled examples but also quite different from how humans learn. We use a setup in which an artificial agent first learns in a simulated world through self-supervised, curiosity-driven exploration. Following this initial learning phase, the learned representations can be used to quickly associate semantic concepts such as different types of doors using one or more labeled examples. To do this, we use a method we call fast concept mapping which uses correlated firing patterns of neurons to define and detect semantic concepts. This association works instantaneously with very few labeled examples, similar to what we observe in humans in a phenomenon called |
Beschreibung: | Cited by: 0; All Open Access, Hybrid Gold Open Access |
ISSN: | 0162-8828 | DOI: | 10.1109/TPAMI.2023.3323040 | Externe URL: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85174823952&doi=10.1109%2fTPAMI.2023.3323040&partnerID=40&md5=53d2cdcd124ef655b6c340be4f17fd59 |
Zur Langanzeige
Seitenaufrufe
2
Letzte Woche
0
0
Letzter Monat
0
0
geprüft am 04.05.2024