TODO. Various techniques in βrunning networks backwardsβ, definition later.
Prior regularisations for ill-posed inverse problems.
Deep dreams probably fit here (Mahendran and Vedaldi 2015; Simonyan, Vedaldi, and Zisserman 2014; Yosinski et al. 2015). For more on that see Inceptionism: Going Deeper into Neural Networks.
I wonder if the reversible architectures (Chang et al. 2018) method gets us anything here?
My focus is more on inverse problems.
Let us run it backwards.
References
Adler, Jonas, and Ozan Γktem. 2018. βLearned Primal-Dual Reconstruction.β IEEE Transactions on Medical Imaging 37 (6): 1322β32.
Anantha Padmanabha, Govinda, and Nicholas Zabaras. 2021. βSolving Inverse Problems Using Conditional Invertible Neural Networks.β Journal of Computational Physics 433 (May): 110194.
Ardizzone, Lynton, Jakob Kruse, Sebastian Wirkert, Daniel Rahner, Eric W. Pellegrini, Ralf S. Klessen, Lena Maier-Hein, Carsten Rother, and Ullrich KΓΆthe. 2019. βAnalyzing Inverse Problems with Invertible Neural Networks.β arXiv:1808.04730 [Cs, Stat], February.
Bao, Gang, Xiaojing Ye, Yaohua Zang, and Haomin Zhou. 2020. βNumerical Solution of Inverse Problems by Weak Adversarial Networks.β Inverse Problems 36 (11): 115003.
Borgerding, Mark, and Philip Schniter. 2016. βOnsager-Corrected Deep Networks for Sparse Linear Inverse Problems.β arXiv:1612.01183 [Cs, Math], December.
Chang, Bo, Lili Meng, Eldad Haber, Lars Ruthotto, David Begert, and Elliot Holtham. 2018. βReversible Architectures for Arbitrarily Deep Residual Neural Networks.β In arXiv:1709.03698 [Cs, Stat].
Depina, Ivan, Saket Jain, Sigurdur Mar Valsson, and Hrvoje Gotovac. 2021. βApplication of Physics-Informed Neural Networks to Inverse Problems in Unsaturated Groundwater Flow.β Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards 0 (0): 1β16.
Franklin, Joel N. 1970. βWell-Posed Stochastic Extensions of Ill-Posed Linear Problems.β Journal of Mathematical Analysis and Applications 31 (3): 682β716.
Genzel, Martin, Jan Macdonald, and Maximilian MΓ€rz. 2020. βSolving Inverse Problems With Deep Neural Networks β Robustness Included?β arXiv:2011.04268 [Cs, Math], November.
Haber, Eldad, and Lars Ruthotto. 2018. βStable Architectures for Deep Neural Networks.β Inverse Problems 34 (1): 014004.
Holl, Philipp, Vladlen Koltun, Kiwon Um, and Nils Thuerey. 2020. βPhiflow: A Differentiable PDE Solving Framework for Deep Learning via Physical Simulations.β In NeurIPS Workshop.
Holl, Philipp, Nils Thuerey, and Vladlen Koltun. 2020. βLearning to Control PDEs with Differentiable Physics.β In ICLR, 5.
Jo, Hyeontae, Hwijae Son, Hyung Ju Hwang, and Eun Heui Kim. 2020. βDeep Neural Network Approach to Forward-Inverse Problems.β Networks & Heterogeneous Media 15 (2): 247.
Kawar, Bahjat, Gregory Vaksman, and Michael Elad. 2021. βSNIPS: Solving Noisy Inverse Problems Stochastically.β In.
Khodayi-Mehr, Reza, and Michael M. Zavlanos. 2019. βVarNet: Variational Neural Networks for the Solution of Partial Differential Equations.β arXiv:1912.07443 [Physics, Stat], December.
Li, Housen, Johannes Schwab, Stephan Antholzer, and Markus Haltmeier. 2020. βNETT: Solving Inverse Problems with Deep Neural Networks.β Inverse Problems 36 (6): 065005.
Lu, Lu, Xuhui Meng, Zhiping Mao, and George Em Karniadakis. 2021. βDeepXDE: A Deep Learning Library for Solving Differential Equations.β SIAM Review 63 (1): 208β28.
Lucas, Alice, Michael Iliadis, Rafael Molina, and Aggelos K. Katsaggelos. 2018. βUsing Deep Neural Networks for Inverse Problems in Imaging: Beyond Analytical Methods.β IEEE Signal Processing Magazine 35 (1): 20β36.
Lunz, Sebastian, Carola Schoenlieb, and Ozan Γktem. 2018. βAdversarial Regularizers in Inverse Problems.β In, 10.
Mahendran, Aravindh, and Andrea Vedaldi. 2015. βUnderstanding Deep Image Representations by Inverting Them.β In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 5188β96.
Mowlavi, Saviz, and Saleh Nabi. 2021. βOptimal Control of PDEs Using Physics-Informed Neural Networks.β arXiv:2111.09880 [Physics], November.
Ogawa, T., Y. Kosugi, and H. Kanada. 1998. βNeural Network Based Solution to Inverse Problems.β In 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227), 3:2471β2476 vol.3.
Rackauckas, Christopher, Yingbo Ma, Vaibhav Dixit, Xingjian Guo, Mike Innes, Jarrett Revels, Joakim Nyberg, and Vijay Ivaturi. 2018. βA Comparison of Automatic Differentiation and Continuous Sensitivity Analysis for Derivatives of Differential Equation Solutions.β arXiv:1812.01892 [Cs], December.
Simonyan, Karen, Andrea Vedaldi, and Andrew Zisserman. 2014. βDeep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.β arXiv:1312.6034 [Cs], April.
Spantini, Alessio, Antti Solonen, Tiangang Cui, James Martin, Luis Tenorio, and Youssef Marzouk. 2015. βOptimal Low-Rank Approximations of Bayesian Linear Inverse Problems.β SIAM Journal on Scientific Computing 37 (6): A2451β87.
Tait, Daniel J., and Theodoros Damoulas. 2020. βVariational Autoencoding of PDE Inverse Problems.β arXiv:2006.15641 [Cs, Stat], June.
Wei, Qi, Kai Fan, Lawrence Carin, and Katherine A. Heller. 2017. βAn Inner-Loop Free Solution to Inverse Problems Using Deep Neural Networks.β arXiv:1709.01841 [Cs], September.
Williams, Christopher, Stefan Klanke, Sethu Vijayakumar, and Kian M. Chai. 2009. βMulti-Task Gaussian Process Learning of Robot Inverse Dynamics.β In Advances in Neural Information Processing Systems 21, edited by D. Koller, D. Schuurmans, Y. Bengio, and L. Bottou, 265β72. Curran Associates, Inc.
Yosinski, Jason, Jeff Clune, Anh Nguyen, Thomas Fuchs, and Hod Lipson. 2015. βUnderstanding Neural Networks Through Deep Visualization.β arXiv:1506.06579 [Cs], June.
Zhang, Dongkun, Ling Guo, and George Em Karniadakis. 2020. βLearning in Modal Space: Solving Time-Dependent Stochastic PDEs Using Physics-Informed Neural Networks.β SIAM Journal on Scientific Computing 42 (2): A639β65.
No comments yet. Why not leave one?