Principles of Intelligence
According to the Oxford American College Dictionary,
a principle is “a general scientific […] law that has
numerous special applications across a wide field,”
describing “a fundamental quality determining the
nature of something.” In its most general definition,
a principle captures relevant and simple regularities.
Ever since SCIoI was founded, we have been conducting research in the fields of both natural and synthetic intelligence. Within the synthetic (i.e. artificial) approach to intelligence research, we were able to identify recurring patterns, representing possible mechanistic principles of intelligence. These are “general scientific […] laws that have numerous special applications across a wide field.” For each of these principles, we could gather empirical support across species, tasks, environments, and levels of abstraction, proving that the principles hold true under many aspects. Our research convincingly shows that mechanistic principles are a suitable approach to understand, characterize, and synthesize intelligence, and in a very general sense, they give us an idea of how the components of intelligence, i.e. the different disciplines, interact with one another. We have identified eight recurring patterns, or principles, of intelligence:
- Active interconnections
- Multiple computational paradigms
- Agent-environment computation
- Adaptive representations (coming soon)
- Multimodality (coming soon)
- Multi-timescale computations (coming soon)
- Incremental assembly of capabilities (coming soon)
- Adaptation of structure (coming soon)
