World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912283115913216 |
|---|---|
| author | Del Ser, Javier Lobo, Jesus L. Müller, Heimo Holzinger, Andreas |
| author_facet | Del Ser, Javier Lobo, Jesus L. Müller, Heimo Holzinger, Andreas |
| contents | World Models help Artificial Intelligence (AI) predict outcomes, reason about its environment, and guide decision-making. While widely used in reinforcement learning, they lack the structured, adaptive representations that even young children intuitively develop. Advancing beyond pattern recognition requires dynamic, interpretable frameworks inspired by Piaget's cognitive development theory. We highlight six key research areas -- physics-informed learning, neurosymbolic learning, continual learning, causal inference, human-in-the-loop AI, and responsible AI -- as essential for enabling true reasoning in AI. By integrating statistical learning with advances in these areas, AI can evolve from pattern recognition to genuine understanding, adaptation and reasoning capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_15168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child Del Ser, Javier Lobo, Jesus L. Müller, Heimo Holzinger, Andreas Artificial Intelligence Computer Vision and Pattern Recognition Emerging Technologies Machine Learning 68T05 World Models help Artificial Intelligence (AI) predict outcomes, reason about its environment, and guide decision-making. While widely used in reinforcement learning, they lack the structured, adaptive representations that even young children intuitively develop. Advancing beyond pattern recognition requires dynamic, interpretable frameworks inspired by Piaget's cognitive development theory. We highlight six key research areas -- physics-informed learning, neurosymbolic learning, continual learning, causal inference, human-in-the-loop AI, and responsible AI -- as essential for enabling true reasoning in AI. By integrating statistical learning with advances in these areas, AI can evolve from pattern recognition to genuine understanding, adaptation and reasoning capabilities. |
| title | World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child |
| topic | Artificial Intelligence Computer Vision and Pattern Recognition Emerging Technologies Machine Learning 68T05 |
| url | https://arxiv.org/abs/2503.15168 |