We propose to use thought-provoking children's questions (TPCQs), namely Highlights BrainPlay questions, to drive artificial intelligence research. These questions are designed to stimulate thought and learning in children, and they can be used to do the same thing in AI systems. We introduce the TPCQ task, which consists of taking a TPCQ question as input and producing as output both (1) answers to the question and (2) learned generalizations. We discuss how BrainPlay questions stimulate learning. We analyze 244 BrainPlay questions, and we report statistics on question type, question class, answer cardinality, answer class, types of knowledge needed, and types of reasoning needed. We find that BrainPlay questions span many aspects of intelligence. We envision an AI system based on the society of mind (Minsky 1986; 2006) consisting of a multilevel architecture with diverse resources that run in parallel to jointly answer and learn from questions. Because the answers to BrainPlay questions and the generalizations learned from them are often highly open-ended, we suggest using human judges for evaluation.
from cs.AI updates on arXiv.org http://ift.tt/1LzdHNs
via IFTTT
No comments:
Post a Comment