Bridging Cognitive Programs and Machine Learning
It addresses the problem of limited adaptability and robustness in AI systems for researchers and practitioners, but is incremental as it only suggests directions without presenting new results.
The paper identifies key shortcomings of modern machine learning in computer vision and reinforcement learning, such as poor performance with scarce data, domain shifts, and lack of intelligent reasoning, and proposes exploratory directions to address these weaknesses.
While great advances are made in pattern recognition and machine learning, the successes of such fields remain restricted to narrow applications and seem to break down when training data is scarce, a shift in domain occurs, or when intelligent reasoning is required for rapid adaptation to new environments. In this work, we list several of the shortcomings of modern machine-learning solutions, specifically in the contexts of computer vision and in reinforcement learning and suggest directions to explore in order to try to ameliorate these weaknesses.