Model-Based Deep Learning
Deep neural networks provide unprecedented performance gains in many real-world problems in signal and image processing. Despite these gains, the future development and practical deployment of deep networks are hindered by their black-box nature, i.e., a lack of interpretability and the need for very large training sets.
In our lab, we are working on model-based deep learning, where the design of learning-based algorithms is based on prior domain knowledge. This approach allows to integrate models and other knowledge about the problem into both the architecture and training process of deep networks. This leads to efficient, high-performance and yet interpretable neural networks which can be employed in a variety of tasks in signal and image processing. Model-based networks require far fewer parameters than their black-box counterparts, generalize better, and can be trained from much less data. In some cases, our networks are trained on a single image, or only on the input itself so that effectively they are unsupervised.
We are developing theory and applications of model-based learning and applying this paradigm to solve a wide variety of tasks, from super-resolution in optical microscopy and ultrasound to speed-of-sound reconstruction using ultrasonography, to the development of modern wireless systems, to image deblurring, signal separation, and more.
References
- V. Monga, Y. Li, and Y. C. Eldar, "Algorithm Unrolling: Interpretable, Efficient Deep Learning for Signal and Image Processing", IEEE Signal Processing Magazine, vol. 38, issue 2, pp. 18-44, March 2021.
- N. Shlezinger, Y. C. Eldar, and S. P. Boyd, "Model-Based Deep Learning: On the Intersection of Deep Learning and Optimization", IEEE Access, vol. 10, pp. 115384-115398, November 2022.
- N. Shlezinger, J. Whang, Y. C. Eldar and A. G. Dimakis, "Model-Based Deep Learning", Proceedings of the IEEE, vol. 111 (5), pp. 465-499, May 2023.
- N. Shlezinger and Y. C. Eldar, "Model-Based Deep Learning", Foundations and Trends in Signal Processing, Vol. 17 (4), pp 291-416, August 2023
- Y. Ben Sahel, J. P. Bryan, B. Cleary, S. L. Farhi and Y. C. Eldar, "Deep Unrolled Recovery in Sparse Biological Imaging", IEEE Signal Processing Magazine, vol. 39 (2), pp. 457-57, February 2022.
-
N. Farsad, N. Shlezinger, A. J. Goldsmith, and Y. C. Eldar, "Data-Driven Symbol Detection via Model-Based Machine Learning", Communications in Information and Systems, vol. 20, issue 3, pp. 283–317, 2020.
-
G. Dardikman-Yoffe and Y. C. Eldar, "Learned SPARCOM: Unfolded Deep Super-Resolution Microscopy", Optics Express, vol. 28, issue 19, pp. 27736-27763, September 2020.
-
O. Bar-Shira, A. Grubstein, Y. Rapson, D. Suhami, E. Atar , K. Peri-Hanania, R. Rosen ,Y. C. Eldar, "Learned Super Resolution Ultrasound for Improved Breast Lesion Characterization", MICCAI 2021.
-
O. Solomon, R. Cohen, Y. Zhang, Y. Yang, H. Qiong, J. Luo, R. J. G. van Sloun and Y. C. Eldar, "Deep Unfolded Robust PCA with Application to Clutter Suppression in Ultrasound", vol. 39, issue 4, pp. 1051-1063, IEEE Transactions on Medical Imaging, April 2020.
-
N. Shlezinger, N. Farsad, Y. C. Eldar, and A. J. Goldsmith, "ViterbiNet: Symbol Detection Using a Deep Learning Based Viterbi Algorithm", IEEE Transactions on Wireless Communications, vol. 19, issue 5, pp. 3319-3331, May 2020.