A Conceptual Framework for Artificial Intelligence Combining Buddhism and the Free Energy Principle

Engineering notes

Key topics: autonomous driving, prediction. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Remarkable advancements in artificial intelligence (AI) have been made in recent years. There is a theory that brain activity in humans is based on the free energy principle, which is a comprehensive theory that attempts to explain the structure and function of cognition and the brain’s behavior. For any self-organized system to be in equilibrium within its environment, the agent performs active inference to minimize the system’s informational free energy and reduce the prediction error from the current presumption. On the other hand, the theory based on the vijñapti-mātratā of Buddhist philosophy explains consciousness through a multilayered structure comprising manifestation and information storage and seems to result in a certain degree of compatibility with AI systems that perform calculations and store information. Therefore, an AI that integrates the vijñapti-mātratā philosophy with the free energy principle could achieve performance, enabling us to perceive not only knowledge but also actions that include human-like emotional expressions. We hereby report that an AI system theory that integrates the theory of vijñapti-mātratā with the principle of free energy.

Links and sources

• PDF from original source

Comments