Authors:
Jhonatan Contreras
1
;
2
and
Thomas Bocklitz
1
;
2
Affiliations:
1
Leibniz Institute of Photonic Technology, Albert Einstein Straße 9, 07745 Jena, Germany
;
2
Institute of Physical Chemistry (IPC) and Abbe Center of Photonics (ACP), Friedrich Schiller University, Helmholtzweg 4, 07743 Jena, Germany
Keyword(s):
Explainabe Artificial Intelligence, Volterra Series, Model Approximation, Model Interpretation.
Abstract:
Convolutional Neural Networks (CNN) have shown remarkable results in several fields in recent years. Traditional performance metrics assess model performance but fail to detect biases in datasets and models. Explainable artificial intelligence (XAI) methods aim to evaluate models, identify biases, and clarify model decisions. We propose an agnostic XAI method based on the Volterra series that approximates models. Our model architecture is composed of three second-order Volterra layers. Relevant information can be extracted from the model to be approximated and used to generate relevance maps that explain the contribution of the input elements to the prediction. Our Volterra-XAI learns its Volterra kernels comprehensively and is trained using a target model outcome. Therefore, no labels are required, and even when training data is unavailable, it is still possible to generate an approximation utilizing similar data. The trustworthiness of our method can be measured by considering the
reliability of the Volterra approximation in comparison with the original model. We evaluate our XAI method for the classification task on 1D Raman spectra and 2D images using two common CNN architectures without hyperparameter tuning. We present relevance maps indicating higher and lower contributions to the approximation prediction (logit).
(More)