Mathematical Perspective of Machine Learning
Machine Learning
2020-07-06 v1 Machine Learning
Abstract
We take a closer look at some theoretical challenges of Machine Learning as a function approximation, gradient descent as the default optimization algorithm, limitations of fixed length and width networks and a different approach to RNNs from a mathematical perspective.
Cite
@article{arxiv.2007.01503,
title = {Mathematical Perspective of Machine Learning},
author = {Yarema Boryshchak},
journal= {arXiv preprint arXiv:2007.01503},
year = {2020}
}
Comments
9 pages 3 figures