Towards Machine Intelligence
It addresses the foundational problem of understanding general intelligence in AI and neuroscience, but it is incremental as it reviews existing theories without proposing a novel solution.
The paper reviews the theoretical concept of a single general-purpose learning algorithm that could explain mental operations, based on the assumption that the brain has innate circuits and all significant algorithms can be learned, but it does not present new experimental results or concrete numbers.
There exists a theory of a single general-purpose learning algorithm which could explain the principles of its operation. This theory assumes that the brain has some initial rough architecture, a small library of simple innate circuits which are prewired at birth and proposes that all significant mental algorithms can be learned. Given current understanding and observations, this paper reviews and lists the ingredients of such an algorithm from both architectural and functional perspectives.