Related papers: Direct Integer Division in RNS and its Hardware So…
In recent advances in solving the problem of transmission network expansion planning, the use of robust optimization techniques has been put forward, as an alternative to stochastic mathematical programming methods, to make the problem…
We propose a novel direct sampling method (DSM) for the effective and stable inversion of the Radon transform. The DSM is based on a generalization of the important almost orthogonality property in classical DSMs to fractional order Sobolev…
Recent works demonstrated the promise of using resistive random access memory (ReRAM) as an emerging technology to perform inherently parallel analog domain in-situ matrix-vector multiplication -- the intensive and key computation in DNNs.…
Compared to classical deep neural networks its binarized versions can be useful for applications on resource-limited devices due to their reduction in memory consumption and computational demands. In this work we study deep neural networks…
Recently we have shown that an architecture based on resistive processing unit (RPU) devices has potential to achieve significant acceleration in deep neural network (DNN) training compared to today's software-based DNN implementations…
The execution of large deep neural networks (DNN) at mobile edge devices requires considerable consumption of critical resources, such as energy, while imposing demands on hardware capabilities. In approaches based on edge computing the…
Dimensionality reduction is an essential technique for multi-way large-scale data, i.e., tensor. Tensor ring (TR) decomposition has become popular due to its high representation ability and flexibility. However, the traditional TR…
In (\cite{zhang2014nonlinear,zhang2014nonlinear2}), we have viewed machine learning as a coding and dimensionality reduction problem, and further proposed a simple unsupervised dimensionality reduction method, entitled deep distributed…
One fruitful formulation of Deep Networks (DNs) enabling their theoretical study and providing practical guidelines to practitioners relies on Piecewise Affine Splines. In that realm, a DN's input-mapping is expressed as per-region affine…
Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate segmentation result with just a few clicks, for some unknown…
Physics-Informed Neural Networks (PINNs) offer a powerful paradigm for flow reconstruction, seamlessly integrating sparse velocity measurements with the governing Navier-Stokes equations to recover complete velocity and latent pressure…
Implicit Neural Representation (INR) is an innovative approach for representing complex shapes or objects without explicitly defining their geometry or surface structure. Instead, INR represents objects as continuous functions. Previous…
Recurrent neural networks (RNN) are used in many real-world text and speech applications. They include complex modules such as recurrence, exponential-based activation, gate interaction, unfoldable normalization, bi-directional dependence,…
Recent approaches for music source separation are almost exclusively based on deep neural networks, mostly employing recurrent neural networks (RNNs). Although RNNs are in many cases superior than other types of deep neural networks for…
Deep neural networks (DNNs) play an increasingly important role in various computer systems. In order to create these networks, engineers typically specify a desired topology, and then use an automated training algorithm to select the…
Recent research demonstrated the promise of using resistive random access memory (ReRAM) as an emerging technology to perform inherently parallel analog domain in-situ matrix-vector multiplication -- the intensive and key computation in…
Can we take a recurrent neural network (RNN) trained to translate between languages and augment it to support a new natural language without retraining the model from scratch? Can we fix the faulty behavior of the RNN by replacing portions…
Speaker-independent speech separation has achieved remarkable performance in recent years with the development of deep neural network (DNN). Various network architectures, from traditional convolutional neural network (CNN) and recurrent…
High-performance clusters and datacenters pose increasingly demanding requirements on storage systems. If these systems do not operate at scale, applications are doomed to become I/O bound and waste compute cycles. To accelerate the data…
We study the classic subgraph enumeration problem under distributed settings. Existing solutions either suffer from severe memory crisis or rely on large indexes, which makes them impractical for very large graphs. Most of them follow a…