Keywords

Convolutional Neural Networks; Deep Learning; Model Interpretability; Feature Visualization; Explainable Artificial Intelligence

References

[1] Taye MM. Theoretical understanding of convolutional neural network: concepts, architectures, applications, future directions. Computation. 2023;11(3):52.

[2] Alzubaidi L, Zhang J, Humaidi AJ, Al-Dujaili A, Duan Y, Al-Shamma O, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021;8(1):53.

[3] Parmar UPS, Surico PL, Singh RB, Goparaju AS. Artificial intelligence (AI) for early diagnosis of retinal diseases. Medicina. 2024;60(4):527.

[4] Ali S, Abuhmed T, El-Sappagh S, Muhammad K, Alonso-Moral JM, Confalonieri R, et al. Explainable artificial intelligence (XAI): what we know and what is left to attain trustworthy artificial intelligence. Inf Fusion. 2023;99:101805.

[5] Kim B, Wattenberg M, Gilmer J, Cai C, Wexler J, Viegas F, et al. Interpretability beyond feature attribution: quantitative testing with concept activation vectors (TCAV). arXiv. 2017. Available from: https://arxiv.org/abs/1711.11279v5

[6] LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278-324.

[7] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1097-105.

[8] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv. 2014. Available from: https://arxiv.org/abs/1409.1556

[9] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv. 2015. Available from: https://arxiv.org/abs/1512.03385

[10] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. arXiv. 2014. Available from: https://arxiv.org/abs/1409.4842

[11] Jamtsho Y, Yangden P, Wangmo S, Lhaden, Pema, Tshering K, et al. Deep learning-based Dzongkha handwritten digit classification. J Inf Technol Comput Eng. 2024;8(1):1-7.

[12] DEEPLIZARD. Interactive demo - convolution operation [Internet]. Available from: https://deeplizard.com/resource/pavq7noze2

[13] DEEPLIZARD. Interactive demo - max pooling operation [Internet]. Available from: https://deeplizard.com/resource/pavq7noze3

[14] Wang ZJ, Turko R, Shaikh O, Park H, Das N, Hohman F, et al. CNN explainer: learning convolutional neural networks with interactive visualization. IEEE Trans Vis Comput Graph. 2021;27(2):1396-406.

[15] Harley AW. An interactive node-link visualization of convolutional neural networks. In: Bebis G, Boyle R, Parvin B, Koracin D, editors. Advances in visual computing. Cham: Springer International Publishing; 2015. p. 867-77.

[16] Roeder L. Netron: visualizer for neural network, deep learning, and machine learning models [Internet]. Zenodo; 2017. Available from: https://doi.org/10.5281/zenodo.5854962

[17] Abadi M, Barham P, Chen J, Chen Z, Davis A, Dean J, et al. TensorFlow: a system for large-scale machine learning. arXiv. 2016. Available from: https://arxiv.org/abs/1605.08695

[18] Gildenblat J. PyTorch library for CAM methods [Internet]. GitHub; 2021. Available from: https://github.com/jacobgil/pytorch-gradcam

[19] Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int J Comput Vis. 2020;128(2):336-59.

[20] Lundberg SM, Lee SI. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst. 2017;30:4765-74.

[21] Ozbulak U. PyTorch CNN visualizations [Internet]. GitHub; 2019. Available from: https://github.com/utkuozbulak/pytorch-cnn-visualizations

[22] Arya V, Bellamy RKE, Chen PY, Dhurandhar A, Hind M, Hoffman SC, et al. One explanation does not fit all: a toolkit and tax-onomy of AI explainability techniques. arXiv. 2019. Available from: https://arxiv.org/abs/1909.03012

[23] Bojarski M, Choromanska A, Choromanski K, Firner B, Jackel L, Muller U, et al. VisualBackProp: efficient visualization of CNNs. arXiv. 2017. Available from: https://arxiv.org/abs/1611.05418

[24] Yosinski J, Clune J, Nguyen A, Fuchs T, Lipson H. Understanding neural networks through deep visualization. arXiv. 2015. Available from: https://arxiv.org/abs/1506.06579

[25] Ribeiro MT, Singh S, Guestrin C. “Why should I trust you?”: explaining the predictions of any classifier. arXiv. 2016. Available from: https://arxiv.org/abs/1602.04938

[26] Shrikumar A, Greenside P, Kundaje A. Learning important features through propagating activation differences. arXiv. 2019. Available from: https://arxiv.org/abs/1704.02685

[27] Zhang L, Zhang P, Ma X, Zhang S, Tao Y, Li W, et al. A generalized language model in tensor space. arXiv. 2019. Available from: https://arxiv.org/abs/1901.11167

[28] Carter S, Armstrong Z, Schubert L, Johnson I, Olah C. Activation atlas. Distill. 2019;4(3):e15.

[29] Rauber J, Zimmermann R, Bethge M, Brendel W. Foolbox native: fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX. J Open Source Softw. 2020;5(53):2607.

[30] Alber M, Lapuschkin S, Seegerer P, Hägele M, Schütt KT, Montavon G, et al. iNNvestigate neural networks! J Mach Learn Res. 2019;20(93):1-8.

[31] Bau D, Zhou B, Khosla A, Oliva A, Torralba A. Network dissection: quantifying interpretability of deep visual representations. arXiv. 2017. Available from: https://arxiv.org/abs/1704.05796

[32] Mopuri KR, Garg U, Babu RV. CNN fixations: an unraveling approach to visualize the discriminative image regions. arXiv. 2018. Available from: https://arxiv.org/abs/1708.06670