Modern Deep Learning for Tabular Data: Novel Approaches to Common Modeling Problems

© The Author(s), under exclusive license to APress Media, LLC, part of Springer Nature 2023

A. Ye, Z. WangModern Deep Learning for Tabular Datahttps://doi.org/10.1007/978-1-4842-8692-0_5

5. Applying Recurrent Structures to Tabular Data

Andre Ye¹   and Zian Wang²

(1)

Seattle, WA, USA

(2)

Redmond, WA, USA

 

I have to write in sequence and only in sequence.

—Andrew Scott, Actor

Chapter 4 demonstrated the application of convolutional neural networks both to images and signals (their “natural” data domain), as well as to tabular data through clever tricks – soft ordering, DeepInsight, and IGTD. This chapter will pursue a similar path of exploration: exploring the application of recurrent networks, traditionally applied to sequences like text and signals, to ...