A Theory of Natural Intelligence
This work addresses foundational questions in AI and neuroscience about the mechanisms of natural intelligence, but it is incremental as it builds on existing literature to propose a theoretical argument.
The paper tackles the problem of understanding why natural intelligence outperforms current AI in learning speed, generalization, and creativity, proposing that the brain's structural regularity, in the form of net fragments, serves as a powerful inductive bias to enable these capabilities.
Introduction: In contrast to current AI technology, natural intelligence -- the kind of autonomous intelligence that is realized in the brains of animals and humans to attain in their natural environment goals defined by a repertoire of innate behavioral schemata -- is far superior in terms of learning speed, generalization capabilities, autonomy and creativity. How are these strengths, by what means are ideas and imagination produced in natural neural networks? Methods: Reviewing the literature, we put forward the argument that both our natural environment and the brain are of low complexity, that is, require for their generation very little information and are consequently both highly structured. We further argue that the structures of brain and natural environment are closely related. Results: We propose that the structural regularity of the brain takes the form of net fragments (self-organized network patterns) and that these serve as the powerful inductive bias that enables the brain to learn quickly, generalize from few examples and bridge the gap between abstractly defined general goals and concrete situations. Conclusions: Our results have important bearings on open problems in artificial neural network research.