Model-based deep learning: Key approaches and design guidelines
Signal processing, communications, and control have traditionally relied on classical
statistical modeling techniques. Such model-based methods tend to be sensitive to …
statistical modeling techniques. Such model-based methods tend to be sensitive to …
Model-based deep learning
Signal processing, communications, and control have traditionally relied on classical
statistical modeling techniques. Such model-based methods utilize mathematical …
statistical modeling techniques. Such model-based methods utilize mathematical …
Learning in latent spaces improves the predictive accuracy of deep neural operators
Operator regression provides a powerful means of constructing discretization-invariant
emulators for partial-differential equations (PDEs) describing physical systems. Neural …
emulators for partial-differential equations (PDEs) describing physical systems. Neural …
Model-based machine learning for communications
Traditional communication systems design is dominated by methods that are based on
statistical models. These statistical-model-based algorithms, which we refer to henceforth as …
statistical models. These statistical-model-based algorithms, which we refer to henceforth as …
Physics-informed deep neural operator networks
Standard neural networks can approximate general nonlinear operators, represented either
explicitly by a combination of mathematical operators, eg in an advection–diffusion reaction …
explicitly by a combination of mathematical operators, eg in an advection–diffusion reaction …
Modeling and training of neural processing systems
E Kusmenko, S Nickels, S Pavlitskaya… - 2019 ACM/IEEE …, 2019 - ieeexplore.ieee.org
The field of deep learning has become more and more pervasive in the last years as we
have seen varieties of problems being solved using neural processing techniques. Image …
have seen varieties of problems being solved using neural processing techniques. Image …
Understanding deep neural networks through input uncertainties
JJ Thiagarajan, I Kim, R Anirudh… - ICASSP 2019-2019 …, 2019 - ieeexplore.ieee.org
Techniques for understanding the functioning of complex machine learning models are
becoming increasingly popular, not only to improve the validation process, but also to extract …
becoming increasingly popular, not only to improve the validation process, but also to extract …
Theoretical Insights into Neural Networks and Deep Learning: Advancing Understanding, Interpretability, and Generalization
UA Usmani, MU Usmani - 2023 World Conference on …, 2023 - ieeexplore.ieee.org
This work aims to provide profound insights into neural networks and deep learning,
focusing on their functioning, interpretability, and generalization capabilities. It explores …
focusing on their functioning, interpretability, and generalization capabilities. It explores …
Two applications of deep learning in the physical layer of communication systems
E Björnson, P Giselsson - arXiv preprint arXiv:2001.03350, 2020 - arxiv.org
Deep learning has proved itself to be a powerful tool to develop data-driven signal
processing algorithms for challenging engineering problems. By learning the key features …
processing algorithms for challenging engineering problems. By learning the key features …
Reliable extrapolation of deep neural operators informed by physics or sparse observations
Deep neural operators can learn nonlinear mappings between infinite-dimensional function
spaces via deep neural networks. As promising surrogate solvers of partial differential …
spaces via deep neural networks. As promising surrogate solvers of partial differential …