XBNet : An Extremely Boosted Neural Network

06/09/2021
by   Tushar Sarkar, et al.
0

Neural networks have proved to be very robust at processing unstructured data like images, text, videos, and audio. However, it has been observed that their performance is not up to the mark in tabular data; hence tree-based models are preferred in such scenarios. A popular model for tabular data is boosted trees, a highly efficacious and extensively used machine learning method, and it also provides good interpretability compared to neural networks. In this paper, we describe a novel architecture XBNet, which tries to combine tree-based models with that of neural networks to create a robust architecture trained by using a novel optimization technique, Boosted Gradient Descent for Tabular Data which increases its interpretability and performance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/19/2018

Deep Neural Decision Trees

Deep neural networks have been proven powerful at processing perceptual ...
research
06/11/2023

Improving the Validity of Decision Trees as Explanations

In classification and forecasting with tabular data, one often utilizes ...
research
11/04/2021

Imagine Networks

In this paper, we introduce an Imagine Network that can simulate itself ...
research
07/18/2022

Why do tree-based models still outperform deep learning on tabular data?

While deep learning has enabled tremendous progress on text and image da...
research
04/08/2023

Pump It Up: Predict Water Pump Status using Attentive Tabular Learning

Water crisis is a crucial concern around the globe. Appropriate and time...
research
05/25/2022

On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity

Most complex machine learning and modelling techniques are prone to over...
research
02/04/2022

Backpropagation Neural Tree

We propose a novel algorithm called Backpropagation Neural Tree (BNeural...

Please sign up or login with your details

Forgot password? Click here to reset