Related papers: IMRSim: A Disk Simulator for Interlaced Magnetic R…
Traditionally, DBMSs separate their storage layer from their indexing layer. While the storage layer physically materializes the database and provides low-level access methods to it, the indexing layer on top enables a faster locating of…
Learning representations that generalize well to unknown downstream tasks is a central challenge in representation learning. Existing approaches such as contrastive learning, self-supervised masking, and denoising auto-encoders address this…
Implicit neural representation (INR), in combination with geometric rendering, has recently been employed in real-time dense RGB-D SLAM. Despite active research endeavors being made, there lacks a unified protocol for fair evaluation,…
Robotic applications are continuously striving towards higher levels of autonomy. To achieve that goal, a highly robust and accurate state estimation is indispensable. Combining visual and inertial sensor modalities has proven to yield…
Electronic health record (EHR) is more and more popular, and it comes with applying machine learning solutions to resolve various problems in the domain. This growing research area also raises the need for EHRs accessibility. Medical…
State-of-the-art digital circuit design tools almost exclusively rely on pure and inertial delay for timing simulations. While these provide reasonable estimations at very low execution time in the average case, their ability to cover…
This article develops iterative machine learning (IML) for output tracking. The input-output data generated during iterations to develop the model used in the iterative update. The main contribution of this article to propose the use of…
Hybrid beamforming is an emerging technology for massive multiple-input multiple-output (MIMO) systems due to the advantages of lower complexity, cost, and power consumption. Recently, intelligent reflection surface (IRS) has been proposed…
Supervised Deep-Learning (DL)-based reconstruction algorithms have shown state-of-the-art results for highly-undersampled dynamic Magnetic Resonance Imaging (MRI) reconstruction. However, the requirement of excessive high-quality…
Processing-In-Memory (PIM) is a novel approach that augments existing DRAM memory chips with lightweight logic. By allowing to offload computations to the PIM system, this architecture allows for circumventing the data-bottleneck problem…
Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications. This has found wide-spread adoption in accelerating neural networks for…
Invertible Rescaling Networks (IRNs) and their variants have witnessed remarkable achievements in various image processing tasks like image rescaling. However, we observe that IRNs with deeper networks are difficult to train, thus hindering…
With the recent proposition of skyrmion utilization in racetrack memories at room temperature, skyrmionics has become a very attractive field. However, for the stability of skyrmions, it is essential to incorporate the Dzyaloshinskii-Moriya…
With the increased attention to memristive-based in-memory analog computing (IMAC) architectures as an alternative for energy-hungry computer systems for data-intensive applications, a tool that enables exploring their device- and…
Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental computation in graph analytics, scientific simulation, and sparse deep learning workloads. However, the extreme irregularity of real-world sparse matrices prevents existing…
The storage of medical images is one of the challenges in the medical imaging field. There are variable works that use implicit neural representation (INR) to compress volumetric medical images. However, there is room to improve the…
Modern neural-network-based speech processing systems are typically required to be robust against reverberation, and the training of such systems thus needs a large amount of reverberant data. During the training of the systems, on-the-fly…
An evolution of a magnetic reconnection in a collisionless accretion disk is investigated using a 2.5 dimensional hybrid code simulation. In astrophysical disks, magnetorotational instability (MRI) is considered to play an important role by…
Adaptive representations are increasingly indispensable for reducing the in-memory and on-disk footprints of large-scale data. Usual solutions are designed broadly along two themes: reducing data precision, e.g., through compression, or…
Missing data is common in applied data science, particularly for tabular data sets found in healthcare, social sciences, and natural sciences. Most supervised learning methods only work on complete data, thus requiring preprocessing such as…