A novel method for classification of tabular data using convolutional neural networks

ABSTRACT Convolutional neural networks (CNNs) represent a major breakthrough in image classification. However, there has not been similar progress in applying CNNs, or neural networks of any kind, to classification of tabular data. We developed and evaluated a novel method, TAbular Convolution (TAC), for classification of such data using CNNs by transforming tabular data to images and then classifying the images using CNNs. The transformation is performed by treating each row of tabular data (i.e., vector of features) as an image filter (kernel), and applying the filter to a fixed base image. A CNN is then trained to classify the filtered images. We applied TAC to classification of gene expression data derived from blood samples of patients with bacterial or viral infections. Our results demonstrate that off-the-shelf ResNet can classify the gene expression data as accurately as the current non-CNN state-of-the-art classifiers.