Machine Common Sense (MCS)
Abstract
The Machine Common Sense (MCS) program will explore approaches to enable commonsense reasoning by machines. Recent advances in machine learning have resulted in exciting new artificial intelligence (AI) capabilities in areas such as image recognition, natural language processing, and two-person strategy games such as Chess and Go. In all of these application domains, the machine reasoning is narrow and highly specialized, and the machine must be carefully trained or programmed for every situation. General machine commonsense reasoning, on par with human cognition, remains elusive. MCS will develop computational models that mimic core systems of human cognitive development that are grounded in perceptual, motor, and memory modalities; develop simulated interaction and learning environments to support machine manipulation of grounded concept models; and develop a commonsense knowledge repository to support AI system development. AI systems that are capable of more human-like reasoning will be able to behave reasonably in unforeseen situations.
Document Details
- Document Type
- Accomplishment
- Publication Date
- Oct 01, 2020
- Source ID
- 9a98b31ae89a236bfb054d9520f4efa4