Journal: Journal of Machine Learning and Deep Learning (JMLDL), Volume:1, Issue:1, Pages: 41-46 Download pdf
Authors: Hina Batool, Tahir Abbas, Jamshaid Iqbal Janjua, Sadaqat Ali Ramay
Date: 12-2024
Abstract: Uncertainty estimation in deep learning has emerged as a crucial area of research due to its significance in enhancing model reliability and decision-making in critical applications. This article explores various methods and applications of uncertainty estimation in deep learning, aiming to provide insights into its importance, methods, and potential impact. Through a comprehensive literature review and analysis, the study identifies key findings regarding the effectiveness, limitations, and ethical considerations associated with uncertainty estimation techniques. The results reveal the diverse range of methodologies employed, including Bayesian approaches, ensemble methods, and Monte Carlo sampling, each with its strengths and drawbacks. Furthermore, the article discusses the implications of uncertainty estimation in deep learning for fields such as healthcare, autonomous systems, and safety-critical domains. Overall, this study underscores the significance of uncertainty estimation in deep learning and provides valuable insights for researchers and practitioners in the field.
Keywords: Uncertainty estimation, Deep learning, Decision-making, Ethical considerations, Interpretability, Applications.
References:
[1] Hussain, S. K., Ramay, S. A., Khan, T. A., Huraira, A., Huraira, M. A., Fiaz, M., & Ansari, G. J. (2023). Deep Learning-Based Ophthalmic Disease Detection: A Systematic Review. Journal of Computing & Biomedical Informatics, 6(01), 160-172.
[2] Janjua, J. I., Zulfiqar, S., Khan, T. A., & Ramay, S. A. (2023, November). Activation Function Conundrums in the Modern Machine Learning Paradigm. In 2023 International Conference on Computer and Applications (ICCA) (pp. 1-8). IEEE.
[3] Loquercio, A., Segu, M., & Scaramuzza, D. (2020). A general framework for uncertainty estimation in deep learning. IEEE Robotics and Automation Letters, 5(2), 3153-3160.
[4] Mena, J., Pujol, O., & Vitrià, J. (2021). A survey on uncertainty estimation in deep learning classification systems from a bayesian perspective. ACM Computing Surveys (CSUR), 54(9), 1-35.
[5] Liu, Y., Pagliardini, M., Chavdarova, T., & Stich, S. U. (2021). The peril of popular deep learning uncertainty estimation methods. arXiv preprint arXiv:2112.05000.
[6] Wang, C., Wang, X., Zhang, J., Zhang, L., Bai, X., Ning, X., ... & Hancock, E. (2022). Uncertainty estimation for stereo matching based on evidential deep learning. Pattern Recognition, 124, 108498.
[7] Kuleshov, V., & Deshpande, S. (2022, June). Calibrated and sharp uncertainties in deep learning via density estimation. In International Conference on Machine Learning (pp. 11683-11693). PMLR.
[8] Gawlikowski, J., Tassi, C. R. N., Ali, M., Lee, J., Humt, M., Feng, J., ... & Zhu, X. X. (2023). A survey of uncertainty in deep neural networks. Artificial Intelligence Review, 56(Suppl 1), 1513-1589.
[9] Tohme, T., Vanslette, K., & Youcef-Toumi, K. (2023). Reliable neural networks for regression uncertainty estimation. Reliability Engineering & System Safety, 229, 108811.
[10] Liu, Y., Pagliardini, M., Chavdarova, T., & Stich, S. U. (2021). The peril of popular deep learning uncertainty estimation methods. arXiv preprint arXiv:2112.05000.
[11] Van Molle, P., Verbelen, T., Vankeirsbilck, B., De Vylder, J., Diricx, B., Kimpe, T., ... & Dhoedt, B. (2021). Leveraging the Bhattacharyya coefficient for uncertainty quantification in deep neural networks. Neural Computing and Applications, 33, 10259-10275.
[12] Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., ... & Nahavandi, S. (2021). A review of uncertainty quantification in deep learning: Techniques, applications and challenges. Information fusion, 76, 243-297.
[13] https://www.gatsby.ucl.ac.uk/~balaji/balaji-uncertainty-talk- cifar-dlrl.pdf
[14] Fraz, M. M. et al. FABnet: Feature attention-based network for simultaneous segmentation of microvessels and nerves in routine histology images of oral cancer. Neural Comput. Appl. 32, 9915–9928 (2020).
[15. Wenzel, F., Snoek, J., Tran, D. & Jenatton, R. Hyperparameter ensembles for robustness and uncertainty quantification. Adv. Neural Inf. Process. Syst. 33, 6514–6527 (2020)
[16. Lakshminarayanan, B., Pritzel, A. & Blundell, C. Simple and scalable predictive uncertainty estimation using deep ensembles. Adv. Neural Inf. Process. Syst. 30, 6405–6416 (2017).
[17] Kompa, B., Snoek, J. & Beam, A. L. Second opinion needed: Communicating uncertainty in medical machine learning. npj Digital
Med. 4, 4 (2021).Top of Form
[18] Med. Image Anal., 59 (2020), Article 101557
[19] Magn. Reson. Med., 83 (5) (2020), pp. 1863-1874
[20] Dy J., Krause A. (Eds.), Proceedings of the 35th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 80, PMLR, Stockholmsmässan, Stockholm Sweden (2018), pp. 4907-4916
[21] Carlos Riquelme, George Tucker, and Jasper Snoek. 2018. Deep bayesian bandits showdown: An empirical comparisonof bayesian deep networks for thompson sampling. arXiv preprint arXiv:1802.09127 (2018).
[22] Simone Rossi, Pietro Michiardi, and Maurizio Filippone. 2018. Good Initializations of Variational Bayes for DeepModels. arXiv preprint arXiv:1810.08083 (2018).