A new approach to perturbation tolerance was identified -- the Meta-Cognitive Loop (MCL) -- for responding to contradictions and other anomalies in complex settings. Further investigations with MCL included identifying architectural requirements, and applying MCL to various domains including reinforcement learning, common-sense reasoning, and a task-oriented natural-language interface system. A series of experiments empirically demonstrated the efficacy of MCL in improving the perturbation tolerance of certain machine learning techniques, including ...
In deadline situations the salient resource is time: all preparations must be carried out in advance of the deadline. If action is called for, an appropriate plan must be formulated and enacted before the deadline. This puts interesting constraints on the reasoning that goes into forming the plan and its simultaneous or subsequent execution. Step-logics were introduced as a mechanism for reasoning situated in time. We first describe them in ...
Reports by Author
