Related papers: Artificial Intelligence Accelerators based on Grap…
Optical computing systems deliver unrivalled processing speeds for scalar operations. Yet, integrated implementations have been constrained to low-dimensional tensor operations that fall short of the vector dimensions required for modern…
The matrix element method utilizes ab initio calculations of probability densities as powerful discriminants for processes of interest in experimental particle physics. The method has already been used successfully at previous and current…
This article surveys the landscape of semiconductor materials and devices research for the acceleration of machine learning (ML) algorithms. We observe a disconnect between the semiconductor and device physics and engineering communities,…
Optical computing offers ultrafast, energy-efficient alternatives to conventional digital processors, yet most implementations remain confined to single-channel processing, severely underutilizing light's information capacity. Here we…
Fast modulation and switching of light at visible and near-infrared (vis-NIR) frequencies is of utmost importance for optical signal processing and sensing technologies. No fundamental limit appears to prevent us from designing…
The unique optical and electronic properties of graphene allow one to realize active optical devices. While several types of graphene-based photonic modulators have already been demonstrated, the potential of combining the versatility of…
The ever-increasing demand for processing data with larger machine learning models requires more efficient hardware solutions due to limitations such as power dissipation and scalability. Optics is a promising contender for providing lower…
In recent years, the attention mechanism has demonstrated superior performance in various tasks, leading to the emergence of GAT and Graph Transformer models that utilize this mechanism to extract relational information from…
We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems. Our scheme allows to efficiently employ compute accelerators such as GPUs and FPGAs for the training of…
Graphene serves critical application and research purposes in various fields. However, fabricating high-quality and large quantities of graphene is time-consuming and it requires heavy human resource labor costs. In this paper, we propose a…
Over the past decade, reflection matrix microscopy (RMM) and advanced image reconstruction algorithms have emerged to address the fundamental imaging depth limitations of optical microscopy in thick biological tissues and complex media. In…
Optics is a promising platform in which to help realise the next generation of fast, parallel and energy-efficient computation. We demonstrate a reconfigurable free-space optical multiplier that is capable of over 3000 computations in…
Mesh-based Graph Neural Networks (GNNs) have recently shown capabilities to simulate complex multiphysics problems with accelerated performance times. However, mesh-based GNNs require a large number of message-passing (MP) steps and suffer…
Integrating graphene with plasmonic nanostructures results in multifunctional hybrid systems with enhanced performance for numerous applications. In this work, we take advantage of the remarkable mechanical properties of graphene to combine…
The high computational cost of ab-initio methods limits their application in predicting electronic properties at the device scale. Therefore, an efficient method is needed to map the atomic structure to the electronic structure quickly.…
Inverse-designed nanophotonic devices offer promising solutions for analog optical computation. High-density photonic integration is critical for scaling such architectures toward more complex computational tasks and large-scale…
Graphene has emerged as a novel platform for opto-electronic applications and photodetector, but the inefficient conversion from light to current has so far been an important roadblock. The main challenge has been to increase the light…
We propose LIGHTNE 2.0, a cost-effective, scalable, automated, and high-quality network embedding system that scales to graphs with hundreds of billions of edges on a single machine. In contrast to the mainstream belief that distributed…
Graphene has extraordinary electronic and optical properties and holds great promise for applications in photonics and optoelectronics. Demonstrations including high-speed photodetectors, optical modulators, plasmonic devices, and ultrafast…
The support vector machines (SVM) is one of the most widely used and practical optimization based classification models in machine learning because of its interpretability and flexibility to produce high quality results. However, the big…