Visual Neural Decomposition to Explain Multivariate Data Sets

09/11/2020
by   Johannes Knittel, et al.
0

Investigating relationships between variables in multi-dimensional data sets is a common task for data analysts and engineers. More specifically, it is often valuable to understand which ranges of which input variables lead to particular values of a given target variable. Unfortunately, with an increasing number of independent variables, this process may become cumbersome and time-consuming due to the many possible combinations that have to be explored. In this paper, we propose a novel approach to visualize correlations between input variables and a target output variable that scales to hundreds of variables. We developed a visual model based on neural networks that can be explored in a guided way to help analysts find and understand such correlations. First, we train a neural network to predict the target from the input variables. Then, we visualize the inner workings of the resulting model to help understand relations within the data set. We further introduce a new regularization term for the backpropagation algorithm that encourages the neural network to learn representations that are easier to interpret visually. We apply our method to artificial and real-world data sets to show its utility.

READ FULL TEXT

page 1

page 2

page 3

page 4

page 5

page 7

page 10

page 11

research
08/19/2019

A Co-analysis Framework for Exploring Multivariate Scientific Data

In complex multivariate data sets, different features usually include di...
research
02/20/2022

SOInter: A Novel Deep Energy Based Interpretation Method for Explaining Structured Output Models

We propose a novel interpretation technique to explain the behavior of s...
research
09/02/2020

LAVARNET: Neural Network Modeling of Causal Variable Relationships for Multivariate Time Series Forecasting

Multivariate time series forecasting is of great importance to many scie...
research
06/21/2021

Multivariate Data Explanation by Jumping Emerging Patterns Visualization

Visual Analytics (VA) tools and techniques have shown to be instrumental...
research
09/16/2022

Detection of Interacting Variables for Generalized Linear Models via Neural Networks

The quality of generalized linear models (GLMs), frequently used by insu...
research
03/03/2023

Interpretable Architecture Neural Networks for Function Visualization

In many scientific research fields, understanding and visualizing a blac...
research
07/26/2019

Multivariate Pointwise Information-Driven Data Sampling and Visualization

With increasing computing capabilities of modern supercomputers, the siz...

Please sign up or login with your details

Forgot password? Click here to reset