Application of the Neural Network Dependability Kit in Real-World Environments

12/14/2020
by   Amit Sahu, et al.
0

In this paper, we provide a guideline for using the Neural Network Dependability Kit (NNDK) during the development process of NN models, and show how the algorithm is applied in two image classification use cases. The case studies demonstrate the usage of the dependability kit to obtain insights about the NN model and how they informed the development process of the neural network model. After interpreting neural networks via the different metrics available in the NNDK, the developers were able to increase the NNs' accuracy, trust the developed networks, and make them more robust. In addition, we obtained a novel application-oriented technique to provide supporting evidence for an NN's classification result to the user. In the medical image classification use case, it was used to retrieve case images from the training dataset that were similar to the current patient's image and could therefore act as a support for the NN model's decision and aid doctors in interpreting the results.

READ FULL TEXT

page 8

page 10

research
08/22/2023

Development of a Novel Quantum Pre-processing Filter to Improve Image Classification Accuracy of Neural Network Models

This paper proposes a novel quantum pre-processing filter (QPF) to impro...
research
03/23/2023

Enriching Neural Network Training Dataset to Improve Worst-Case Performance Guarantees

Machine learning algorithms, especially Neural Networks (NNs), are a val...
research
04/21/2022

AU-NN: ANFIS Unit Neural Network

In this paper is described the ANFIS Unit Neural Network, a deep neural ...
research
02/21/2019

Correspondence Analysis Using Neural Networks

Correspondence analysis (CA) is a multivariate statistical tool used to ...
research
05/06/2020

Evaluation, Tuning and Interpretation of Neural Networks for Meteorological Applications

Neural networks have opened up many new opportunities to utilize remotel...
research
07/15/2020

Evaluation of Neural Network Classification Systems on Document Stream

One major drawback of state of the art Neural Networks (NN)-based approa...
research
09/29/2022

Model Zoos: A Dataset of Diverse Populations of Neural Network Models

In the last years, neural networks (NN) have evolved from laboratory env...

Please sign up or login with your details

Forgot password? Click here to reset