Tabular data is the most commonly used form of data in industry . Gradient Boosting Trees, Support Vector Machine, Random Forest, and Logistic Regression are typically used for classification tasks on tabular data… DNN models using categorical embeddings are also applied in this task . Recent work of Super Characters method using two-dimensional word embeds achieved the state of art result in text classification tasks . In this paper, we propose the SuperTML method, which borrows the idea of Super characters method . For each input of tabular . data, the features are first projected into two .dimensional . embeddaries like an image, and then . this image is fed into fine-tuned two- dimensional CNN models for classification . The proposed Super .

Links: PDF - Abstract

Code :

https://github.com/GilesStrong/SuperTML_HiggsML_Test
https://github.com/SSinyu/p

Keywords : data - dimensional - tabular - method - classification -

Leave a Reply

Your email address will not be published. Required fields are marked *

error

Enjoy this blog? Please spread the word :)