Related papers: Training Auto-encoder-based Optimizers for Teraher…
Image dehazing is a crucial image pre-processing task aimed at removing the incoherent noise generated by haze to improve the visual appeal of the image. The existing models use sophisticated networks and custom loss functions which are…
Terahertz (THz) band is expected to be one of the key enabling technologies of the sixth generation (6G) wireless networks because of its abundant available bandwidth and very narrow beam width. Due to high frequency operations,…
The combination of Terahertz (THz) and massive multiple-input multiple-output (MIMO) is promising to meet the increasing data rate demand of future wireless communication systems thanks to the huge bandwidth and spatial degrees of freedom.…
This paper studies the data-driven reconstruction of firing rate dynamics of brain activity described by linear-threshold network models. Identifying the system parameters directly leads to a large number of variables and a highly…
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be solved by finding the eigenvector corresponding to the smallest, or zero, eigenvalue of a matrix…
Terahertz (THz) communication will be a key enabler for next-generation wireless systems. While THz frequency bands provide abundant bandwidth and extremely high data rates, their effective operation is inhibited by short communication…
Terahertz (THz) emission spectroscopy is a powerful method that allows one to measure the ultrafast dynamics of polarization, current, or magnetization in a material based on THz emission from the material. However, the practical…
Visualizing information inside objects is an ever-lasting need to bridge the world from physics, chemistry, biology to computation. Among all tomographic techniques, terahertz (THz) computational imaging has demonstrated its unique sensing…
Compressed sensing techniques enable efficient acquisition and recovery of sparse, high-dimensional data signals via low-dimensional projections. In this work, we propose Uncertainty Autoencoders, a learning framework for unsupervised…
Terahertz imaging holds great potential for non-destructive material inspection, but practical implementation has been limited by resolution constraints. In this study, we present a single-pixel THz imaging system based on a confocal…
Research in Curriculum Learning has shown better performance on the task by optimizing the sequence of the training data. Recent works have focused on using complex reinforcement learning techniques to find the optimal data ordering…
Terahertz communication is one of the most promising wireless communication technologies for 6G generation and beyond. For THz systems to be practically adopted, channel estimation is one of the key issues. We consider the problem of…
Terahertz (THz) systems have the benefit of high bandwidth and hence are capable of supporting ultra-high data rates, albeit at the cost of high pathloss. Hence they tend to harness high-gain beamforming. Therefore a novel hybrid 3D…
Terahertz (THz) communication is a promising technology for future wireless communications, offering data rates of up to several terabits-per-second (Tbps). However, the range of THz band communications is often limited by high pathloss and…
Terahertz Time Domain Spectroscopy (THz-TDS) systems have emerged as mature technologies with significant potential across various research fields and industries. However, the lack of standardized methods for signal and noise estimation and…
Tensor Networks (TN) offer a powerful framework to efficiently represent very high-dimensional objects. TN have recently shown their potential for machine learning applications and offer a unifying view of common tensor decomposition models…
This paper proposes a new methodology to predict and update the residual useful lifetime of a system using a sequence of degradation images. The methodology integrates tensor linear algebra with traditional location-scale regression widely…
Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector…
We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient descent) to quickly solve parametric convex optimization…
A rapidly growing area of research is the use of machine learning approaches such as autoencoders for dimensionality reduction of data and models in scientific applications. We show that the canonical formulation of autoencoders suffers…