Jaime Carbonell
Papers
5
Total Citations
261
H-Index
5
About
Jaime Carbonell is a pioneering figure in artificial intelligence, whose research spans machine learning, natural language processing, and analogical reasoning. He is best known for his foundational work on derivational analogy, a technique that automates case acquisition, storage, and utilization in AI systems. His seminal 1993 paper, "Derivational Analogy in PRODIGY," which has garnered over 198 citations, introduced a framework for learning by reusing past problem-solving experiences, significantly advancing the field of case-based reasoning. Carbonell also contributed to the World Modelers Project, developing simulator architectures for complex systems. His later work on vision-language fusion for object recognition, published in 2017, demonstrates his enduring impact, integrating human contextual cues to improve AI perception. With a career marked by groundbreaking contributions to AI and machine learning, Carbonell’s research has shaped how machines learn from analogies and interact with human knowledge, influencing generations of researchers and practitioners.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Learning by analogical replay in prodigy: First results15 citations · 1991
- 4The World Modelers Project: Objectives and Simulator Architecture9 citations · 1986
- 5Vision-Language Fusion for Object Recognition6 citations · 2017