Related papers: A Silicon Photonic Accelerator for Convolutional N…

Image classification is a fundamental computer vision problem, and neural networks offer efficient solutions. With advancing quantum technology, quantum neural networks have gained attention. However, they work only for low-dimensional data…

Graph Neural Networks (GNNs) use a fully-connected layer to extract features from the nodes of a graph and aggregate these features using message passing between nodes, combining two distinct computational patterns: dense, regular…

Convolutional neural network (CNN) accelerators are being widely used for their efficiency, but they require a large amount of memory, leading to the use of a slow and power consuming external memory. This paper exploits two schemes to…

Determining effective elastic properties of rocks from their pore-scale digital images is a key goal of digital rock physics (DRP). Direct numerical simulation (DNS) of elastic behavior, however, incurs high computational cost; and…

Photonic Microring Resonator (MRR) based hardware accelerators have been shown to provide disruptive speedup and energy-efficiency improvements for processing deep Convolutional Neural Networks (CNNs). However, previous MRR-based CNN…

Holographic displays have significant potential in virtual reality and augmented reality owing to their ability to provide all the depth cues. Deep learning-based methods play an important role in computer-generated holography (CGH). During…

This paper presents a comprehensive evaluation of the potential of Quantum Convolutional Neural Networks (QCNNs) in comparison to classical Convolutional Neural Networks (CNNs) and Artificial / Classical Neural Network (ANN) models. With…

Deep Neural Networks are becoming the de-facto standard models for image understanding, and more generally for computer vision tasks. As they involve highly parallelizable computations, CNN are well suited to current fine grain programmable…

Photonic computing is a computing paradigm which have great potential to overcome the energy bottlenecks of electronic von Neumann architecture. Throughput and power consumption are fundamental limitations of…

Capsules are the name given by Geoffrey Hinton to vector-valued neurons. Neural networks traditionally produce a scalar value for an activated neuron. Capsules, on the other hand, produce a vector of values, which Hinton argues correspond…

Hybrid CNN-Transformer architectures achieve strong results in image super-resolution, but scaling attention windows or convolution kernels significantly increases computational cost, limiting deployment on resource-constrained devices. We…

Modern problems in high-performance computing, ranging from training and inferencing deep learning models in computer vision and language models to simulating complex physical systems with nonlinearly-coupled equations, require exponential…

Computational material modeling using advanced numerical techniques speeds up the design process and reduces the costs of developing new engineering products. In the field of multiscale modeling, huge computation efforts are expected for…

Large machine learning models based on Convolutional Neural Networks (CNNs) with rapidly increasing number of parameters, trained with massive amounts of data, are being deployed in a wide array of computer vision tasks from self-driving…

Convolutional neural networks (CNNs) have demonstrated their capability to solve different kind of problems in a very huge number of applications. However, CNNs are limited for their computational and storage requirements. These limitations…

Quantized Neural Networks (QNNs), which use low bitwidth numbers for representing parameters and performing computations, have been proposed to reduce the computation complexity, storage size and memory usage. In QNNs, parameters and…

The high accuracy of detector simulation is crucial for modern particle physics experiments. However, this accuracy comes with a high computational cost, which will be exacerbated by the large datasets and complex detector upgrades…

This paper proposes a training method having multiple cyclic training for achieving enhanced performance in low-bit quantized convolutional neural networks (CNNs). Quantization is a popular method for obtaining lightweight CNNs, where the…

Efficient model inference is an important and practical issue in the deployment of deep neural network on resource constraint platforms. Network quantization addresses this problem effectively by leveraging low-bit representation and…

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…