Reliability of deep learning
| školitel: | RNDr. Jan Kalina, Ph.D. |
| e-mail: | zobrazit e-mail |
| typ práce: | dizertační práce |
| zaměření: | MINF, APIN |
| klíčová slova: | Deep learning, reliability assessment, diagnostics, error propagation. |
| popis: | Recent research on reliability in the context of deep learning has shown that there is no unique understanding of reliability assessment for training of deep networks, i.e. there is no unity as to which steps should be performed to accompany the training. Statistical approaches to the newly arising field of diagnostics for deep learning start from the simplest ideas such as verification of the trained network on out-of-distribution data. More powerful approaches include verifying the influence of adversarial examples in the data, evaluation of uncertainty within deep learning algorithms, or computational methods for error propagation throughout the network. One of rare theoretical approaches standing on probabilistic reasoning is the hypothesis test of reliability for a multi-class classifier. The thesis will propose novel tools for assessing reliability of trained deep networks. Theoretical investigations will evaluate the influence of possible errors (uncertainty, measurement errors, or outlying measurements) on the results of a trained deep network. Another aim is to derive diagnostic tools for checking the probability assumptions for deep networks. The tools used here may include bootstrapping and nonparametric combinations of tests. |
| literatura: | [1] Alshemali B., Kalita J. (2020). Improving the reliability of deep neural networks in NLP: A review. Knowledge-based systems 191, 105210. [2] Bosio A., Bernardi P., Ruospo A., Sanchez E. (2019). A reliability analysis of a deep neural network. IEEE Latin American Test Symposium LATS 2019, 1-6. [3] Caldeira J., Nord B. (2021). Deeply uncertain: Comparing methods of uncertainty quantification in deep learning algorithms. Machine Learning: Science and Technology 2, 015002. [4] Gweon H. (2023). A power-controlled reliability assessment for multi-class probabilistic classifiers. Advances in Data Analysis and Classification 17, 927-949. [5] Martensson G., Ferreira D., Granberg T., Cavallin L., Oppedal K. et al. (2020). The reliability of a deep learning model in clinical out-of-distribution MRI data: A multicohort study. Medical Image Analysis 66, 101714. |
| naposledy změněno: | 11.04.2025 12:57:42 |
za obsah této stránky zodpovídá:
Ľubomíra Dvořáková | naposledy změněno: 12.9.2011