Coloring black boxes: visualization of neural network decisions

02/23/2018
by   Wlodzislaw Duch, et al.
0

Neural networks are commonly regarded as black boxes performing incomprehensible functions. For classification problems networks provide maps from high dimensional feature space to K-dimensional image space. Images of training vector are projected on polygon vertices, providing visualization of network function. Such visualization may show the dynamics of learning, allow for comparison of different networks, display training vectors around which potential problems may arise, show differences due to regularization and optimization procedures, investigate stability of network classification under perturbation of original vectors, and place new data sample in relation to training data, allowing for estimation of confidence in classification of a given sample. An illustrative example for the three-class Wine data and five-class Satimage data is described. The visualization method proposed here is applicable to any black box system that provides continuous outputs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/06/2022

Generative Evolutionary Strategy For Black-Box Optimizations

Many scientific and technological problems are related to optimization. ...
research
12/17/2022

Two-sample test based on Self-Organizing Maps

Machine-learning classifiers can be leveraged as a two-sample statistica...
research
01/12/2022

SLISEMAP: Explainable Dimensionality Reduction

Existing explanation methods for black-box supervised learning models ge...
research
02/16/2020

REST: Performance Improvement of a Black Box Model via RL-based Spatial Transformation

In recent years, deep neural networks (DNN) have become a highly active ...
research
01/28/2022

3D Visualization and Spatial Data Mining for Analysis of LULC Images

The present study is an attempt made to create a new tool for the analys...
research
11/25/2020

Feature space approximation for kernel-based supervised learning

We propose a method for the approximation of high- or even infinite-dime...
research
05/19/2016

AMSOM: Adaptive Moving Self-organizing Map for Clustering and Visualization

Self-Organizing Map (SOM) is a neural network model which is used to obt...

Please sign up or login with your details

Forgot password? Click here to reset