Export 6 results:
Filters: Keyword is deep learning and Author is Tomaso Poggio [Clear All Filters]
An analysis of training and generalization errors in shallow and deep networks. Neural Networks 121, 229 - 241 (2020).
Theory I: Deep networks and the curse of dimensionality. Bulletin of the Polish Academy of Sciences: Technical Sciences 66, (2018).
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks. arXiv.org (2017). at <https://arxiv.org/abs/1711.01530>
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review. International Journal of Automation and Computing 1-17 (2017). doi:10.1007/s11633-017-1054-2