Keio Univ. Yagami-campus, Building 14, Room 733
3-14-1 Kouhoku-ku, Hiyoshi, Yokohama 223-8522, JAPAN
Title: Tropical geometry of Deep Neural Networks
Abstract: We give a review on the paper “Tropical Geometry of Deep Neural Networks”, which is published in ICML 2018.
https://arxiv.org/pdf/1805.07091.pdf
They establish a connection between feedforward neural networks with ReLU activation function and Tropical geometry, which is a field in Mathematics to treat piecewise linear functions. Precisely speaking, they show that the family of such neural networks is equivalent to the family of tropical rational maps.
We start with a brief introduction to Tropical geometry and see their result.
Please feel free to join.
Best regards,
Akiyoshi Sannai
Public events of RIKEN Center for Advanced Intelligence Project (AIP)
Join community