Machine Learning From Conversation With Humans
Abstract
Human social learning is an effective process that has inspired many existing machine learning techniques, such as learning from observation and learning by demonstration. Hence, in this paper, we are proposing another form of social learning, Learning from a Conversation (LfC). LfC is an open-ended machine learning system in which an artificially intelligent agent learns from extended dialog with a human. Our system enables the agent to adapt to new changes based on the human input. We provide a detailed description of our system and report its performance by providing several examples that reflect our system's efficiency. Test results indicate that the prototype was successful in learning from conversation.
Publication Date
1-1-2017
Publication Title
FLAIRS 2017 - Proceedings of the 30th International Florida Artificial Intelligence Research Society Conference
Number of Pages
2-7
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
85029473654 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85029473654
STARS Citation
Ali, Awrad Mohammed and Gonzalez, Avelino J., "Machine Learning From Conversation With Humans" (2017). Scopus Export 2015-2019. 6613.
https://stars.library.ucf.edu/scopus2015/6613