Causality-Aware Convolutional Neural Networks for Advanced Image Classification and Generation
Terziyan, V., & Vitko, O. (2023). Causality-Aware Convolutional Neural Networks for Advanced Image Classification and Generation. In F. Longo, M. Affenzeller, A. Padovano, & S. Weiming (Eds.), 4th International Conference on Industry 4.0 and Smart Manufacturing (pp. 495-506). Elsevier. Procedia Computer Science, 217. https://doi.org/10.1016/j.procs.2022.12.245
Published inProcedia Computer Science
© 2022 The Authors. Published by Elsevier B.V.
Smart manufacturing uses emerging deep learning models, and particularly Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), for different industrial diagnostics tasks, e.g., classification, detection, recognition, prediction, synthetic data generation, security, etc., on the basis of image data. In spite of being efficient for these objectives, the majority of current deep learning models lack interpretability and explainability. They can discover features hidden within input data together with their mutual co-occurrence. However, they are weak at discovering and making explicit hidden causalities between the features, which could be the reason behind the particular diagnoses. In this paper, we suggest Causality-Aware CNNs (CA-CNNs) and Causality-Aware GANs (CA-GANs) to address the issue of learning hidden causalities within images. The core architecture includes an additional layer of neurons (after the last convolution-pooling and just before the dense layers), which learns pairwise conditional probabilities (aka causality estimates) for the features. Computations for these neurons are driven by the adaptive Lehmer mean function. Learned causalities are merged with the features during flattening and (via fully connected layers) influence the classification outcomes. Such causality estimates can be done for the mixed inputs where images are combined with other data. We argue that CA-CNNs not only improve the classification performance of normal CNNs but also open additional opportunities for the explainability of the models’ outcomes. We consider as an additional advantage for CA-CNNs (if used as a discriminator within CA-GANs) the possibility to generate realistically looking images with respect to the causalities. ...
ConferenceInternational Conference on Industry 4.0 and Smart Manufacturing
Is part of publication4th International Conference on Industry 4.0 and Smart Manufacturing
ISSN Search the Publication Forum1877-0509
Publication in research information system
MetadataShow full item record
Showing items with similar title or keywords.
Convolutional Neural Network Based Sleep Stage Classification with Class Imbalance Xu, Qi; Zhou, Dongdong; Wang, Jian; Shen, Jiangrong; Kettunen, Lauri; Cong, Fengyu (IEEE, 2022)Accurate sleep stage classification is vital to assess sleep quality and diagnose sleep disorders. Numerous deep learning based models have been designed for accomplishing this labor automatically. However, the class ...
Hyper-flexible Convolutional Neural Networks based on Generalized Lehmer and Power Means Terziyan, Vagan; Malyk, Diana; Golovianko, Mariia; Branytskyi, Vladyslav (Elsevier, 2022)Convolutional Neural Network is one of the famous members of the deep learning family of neural network architectures, which is used for many purposes, including image classification. In spite of the wide adoption, such ...
The Truth is Out There : Focusing on Smaller to Guess Bigger in Image Classification Terziyan, Vagan; Kaikova, Olena; Malyk, Diana; Branytskyi, Vladyslav (Elsevier, 2023)In Artificial Intelligence (AI) in general and in Machine Learning (ML) in particular, which are important and integral components of modern Industry 4.0, we often deal with uncertainty, e.g., lack of complete information ...
DeepFake knee osteoarthritis X-rays from generative adversarial neural networks deceive medical experts and offer augmentation potential to automatic classification Prezja, Fabi; Paloneva, Juha; Pölönen, Ilkka; Niinimäki, Esko; Äyrämö, Sami (Nature Publishing Group, 2022)Recent developments in deep learning have impacted medical science. However, new privacy issues and regulatory frameworks have hindered medical data sharing and collection. Deep learning is a very data-intensive process ...
Neutrino interaction classification with a convolutional neural network in the DUNE far detector DUNE Collaboration (American Physical Society, 2020)The Deep Underground Neutrino Experiment is a next-generation neutrino oscillation experiment that aims to measure CP-violation in the neutrino sector as part of a wider physics program. A deep learning approach based on ...