Deep learning methods for solving linear inverse problems: Research directions and paradigms
The linear inverse problem is fundamental to the development of various scientific areas.
Innumerable attempts have been carried out to solve different variants of the linear inverse …
Innumerable attempts have been carried out to solve different variants of the linear inverse …
A survey on deep matrix factorizations
Constrained low-rank matrix approximations have been known for decades as powerful
linear dimensionality reduction techniques able to extract the information contained in large …
linear dimensionality reduction techniques able to extract the information contained in large …
Towards automatic concept-based explanations
Interpretability has become an important topic of research as more machine learning (ML)
models are deployed and widely used to make important decisions. Most of the current …
models are deployed and widely used to make important decisions. Most of the current …
Detecting silicone mask-based presentation attack via deep dictionary learning
In movies, film stars portray another identity or obfuscate their identity with the help of
silicone/latex masks. Such realistic masks are now easily available and are used for …
silicone/latex masks. Such realistic masks are now easily available and are used for …
Deep neural network structures solving variational inequalities
PL Combettes, JC Pesquet - Set-Valued and Variational Analysis, 2020 - Springer
Motivated by structures that appear in deep neural networks, we investigate nonlinear
composite models alternating proximity and affine operators defined on different spaces. We …
composite models alternating proximity and affine operators defined on different spaces. We …
Simultaneous detection of multiple appliances from smart-meter measurements via multi-label consistent deep dictionary learning and deep transform learning
Currently there are several well-known approaches to non-intrusive appliance load
monitoring-rule based, stochastic finite state machines, neural networks, and sparse coding …
monitoring-rule based, stochastic finite state machines, neural networks, and sparse coding …
Learning structure and strength of CNN filters for small sample size training
Abstract Convolutional Neural Networks have provided state-of-the-art results in several
computer vision problems. However, due to a large number of parameters in CNNs, they …
computer vision problems. However, due to a large number of parameters in CNNs, they …
Selective prototype network for few-shot metal surface defect segmentation
Metal surface defects segmentation is a critical task to make pixel-level predictions about
defects in the industrial production process, which has great significance in improving …
defects in the industrial production process, which has great significance in improving …
Moving force identification based on learning dictionary with double sparsity
Moving force identification (MFI) is essential for the bridge safety as it is one of the major
loads acting on the bridge deck. MFI techniques based on force dictionary are promising …
loads acting on the bridge deck. MFI techniques based on force dictionary are promising …
A computational approach to aid clinicians in selecting anti-viral drugs for COVID-19 trials
A Mongia, SK Saha, E Chouzenoux, A Majumdar - Scientific reports, 2021 - nature.com
The year 2020 witnessed a heavy death toll due to COVID-19, calling for a global
emergency. The continuous ongoing research and clinical trials paved the way for vaccines …
emergency. The continuous ongoing research and clinical trials paved the way for vaccines …