Towards Machine Intelligence
Artificial Intelligence
2016-03-30 v1 Machine Learning
Neural and Evolutionary Computing
Abstract
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.
Cite
@article{arxiv.1603.08262,
title = {Towards Machine Intelligence},
author = {Kamil Rocki},
journal= {arXiv preprint arXiv:1603.08262},
year = {2016}
}
Comments
10 pages, submitted to AGI-16. arXiv admin note: substantial text overlap with arXiv:1512.01926