Point classification with Runge-Kutta networks and feature space augmentation

04/06/2021
by   Elisa Giesecke, et al.
19

In this paper we combine an approach based on Runge-Kutta Nets considered in [Benning et al., J. Comput. Dynamics, 9, 2019] and a technique on augmenting the input space in [Dupont et al., NeurIPS, 2019] to obtain network architectures which show a better numerical performance for deep neural networks in point classification problems. The approach is illustrated with several examples implemented in PyTorch.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 10

page 11

page 18

page 19

05/03/2021

Estimation of underreporting in Brazilian tuberculosis data, 2012-2014

Analysis of burden of underregistration in tuberculosis data in Brazil, ...
05/06/2021

Probablistic Bigraphs

Bigraphs are a universal computational modelling formalism for the spati...
08/21/2017

Deep vs. Diverse Architectures for Classification Problems

This study compares various superlearner and deep learning architectures...
01/15/2013

The Neural Representation Benchmark and its Evaluation on Brain and Machine

A key requirement for the development of effective learning representati...
10/10/2018

Response to Comment on "All-optical machine learning using diffractive deep neural networks"

In their Comment, Wei et al. (arXiv:1809.08360v1 [cs.LG]) claim that our...
11/19/2018

Reinforcement Learning with A* and a Deep Heuristic

A* is a popular path-finding algorithm, but it can only be applied to th...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.