Enhancing Safety and Efficiency through Explainable Transfer Learning
<p id="p1">This chapter explores the integral role of explainable transfer learning in AI, focusing on its applications across varied domains. It begins by examining the nuances of domain differences, emphasizing how understanding these disparities is vital for effective model transfer. The discussi...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Capítulo de libro |
| Lenguaje: | inglés |
| Publicado: |
IntechOpen
2024
|
| Materias: | |
| Acceso en línea: | https://www.intechopen.com/chapters/89727 |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | <p id="p1">This chapter explores the integral role of explainable transfer learning in AI, focusing on its applications across varied domains. It begins by examining the nuances of domain differences, emphasizing how understanding these disparities is vital for effective model transfer. The discussion then shifts to identifying optimal parameters for transfer, addressing the challenges of adapting models to different contexts. Finally, the chapter highlights the use of representational models in reinforcement learning, demonstrating how explainable action advising enhances learning efficiency and safety. Throughout, the chapter underscores the importance of explainability in transfer learning, showcasing its ability to facilitate domain adaptation, optimize parameter selection, and provide actionable insights, thereby ensuring more robust and reliable AI applications.</p> |
|---|---|
| ISBN: | 978-0-85014-246-4 |
| DOI: | 10.5772/intechopen.115536 |