投影:人工知能における人間らしい推論のメカニズム
Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence
視覚・ロボティクス・言語など様々なAI領域で、モデルからのトップダウン情報を活用する「投影」推論が、未知・困難な状況への知識適用を可能にする鍵となることを示した論文。
著者: Frank Guerin
分類: cs.AI, cs.CV, cs.RO
原文アブストラクト
Artificial Intelligence systems cannot yet match human abilities to apply knowledge to situations that vary from what they have been programmed for, or trained for. In visual object recognition methods of inference exploiting top-down information (from a model) have been shown to be effective for recognising entities in difficult conditions. Here this type of inference, called `projection', is shown to be a key mechanism to solve the problem of applying knowledge to varied or challenging situations, across a range of AI domains, such as vision, robotics, or language. Finally the relevance of projection to tackling the commonsense knowledge problem is discussed.
