SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data.

2 Hits in 3.1 sec

2 Hits

in 3.1 sec

In this paper, we propose the SuperTML method, which borrows the idea of Super Characters method and two-dimensional embeddings to address the problem of classification on tabular data. ... For each input of tabular data, the features are first projected into two-dimensional embeddings like an image, and then this image is fed into fine-tuned two-dimensional CNN models for classification. ... For each input, tabular features are first projected onto a two-dimensional embedding and fed into finetuned two-dimensional CNN models for classification. ...

arXiv:1903.06246v3 fatcat:bd35n4p5qfbadcoqbl4pn6llfe

Multiple Versions

For each input of tabular data, the features are first projected into twodimensional embeddings like an image, and then this image is fed into fine-tuned two-dimensional CNN models for classification. ... In this paper, we propose the Su-perTML method, which borrows the idea of Super Characters method and two-dimensional embeddings to address the problem of classification on tabular data. ... Recent research has tried using one-dimensional embedding and implementing RNNs or one-dimensional CNNs to address the TML (Tabular data Machine Learning) tasks, or tasks that deal with structured data ...

doi:10.1109/cvprw.2019.00360 dblp:conf/cvpr/SunYZLDYD19 fatcat:5ncrmjdrgjajbeax3mxn3rc7c4

SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data [article]

Preserved Fulltext

Other Versions

SuperTML: Two-Dimensional Word Embedding for the Precognition on Structured Tabular Data

Preserved Fulltext