Related papers: Programmable Optical Spectrum Shapers as Computing…
Over-fitting-based image compression requires weights compactness for compression and fast convergence for practical use, posing challenges for deep convolutional neural networks (CNNs) based methods. This paper presents a simple…
There exists a significant scale gap between photonic neural network integrated chips and neural networks, which hinders the deployment and application of photonic neural network. Here, we propose hardware-aware lightweight spiking neural…
Light-weight convolutional neural networks (CNNs) suffer performance degradation as their low computational budgets constrain both the depth (number of convolution layers) and the width (number of channels) of CNNs, resulting in limited…
Recently, machine learning had a remarkable impact, from scientific to everyday-life applications. However, complex tasks often imply unfeasible energy and computational power consumption. Quantum computation might lower such requirements,…
On-chip photonic processors for neural networks have potential benefits in both speed and energy efficiency but have not yet reached the scale at which they can outperform electronic processors. The dominant paradigm for designing on-chip…
Convolutional neural networks (CNNs) have rapidly risen in popularity for many machine learning applications, particularly in the field of image recognition. Much of the benefit generated from these networks comes from their ability to…
Recently, convolutional neural networks (CNN) have demonstrated impressive performance in various computer vision tasks. However, high performance hardware is typically indispensable for the application of CNN models due to the high…
Deep convolutional neural networks (CNNs) have shown excellent performance in object recognition tasks and dense classification problems such as semantic segmentation. However, training deep neural networks on large and sparse datasets is…
It is well known that attention mechanisms can effectively improve the performance of many CNNs including object detectors. Instead of refining feature maps prevalently, we reduce the prohibitive computational complexity by a novel attempt…
In StyleGAN, convolution kernels are shaped by both static parameters shared across images and dynamic modulation factors $w^+\in\mathcal{W}^+$ specific to each image. Therefore, $\mathcal{W}^+$ space is often used for image inversion and…
Convolutional neural networks have shown great success on feature extraction from raw input data such as images. Although convolutional neural networks are invariant to translations on the inputs, they are not invariant to other…
Neural Networks (NNs) have become the mainstream technology in the artificial intelligence (AI) renaissance over the past decade. Among different types of neural networks, convolutional neural networks (CNNs) have been widely adopted as…
The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architectures have proposed reduced complexity versions (e.g.…
Spiking neural networks (SNNs) can be used in low-power and embedded systems (such as emerging neuromorphic chips) due to their event-based nature. Also, they have the advantage of low computation cost in contrast to conventional artificial…
It is assumed that pre-training provides the feature extractor with strong class transferability and that high novel class generalization can be achieved by simply reusing the transferable feature extractor. In this work, our motivation is…
With the rapid growth in the semiconductor industry, it is becoming critical to detect and classify increasingly smaller patterned defects. Recently machine learning, including deep learning, has come to aid in this endeavor in a big way.…
Purpose- High speed image processing is a challenging task for real-time applications such as product quality control of manufacturing lines. Smart image sensors use an array of in-pixel processors to facilitate high-speed real-time image…
Spiking neural networks (SNNs) that enable low-power design on edge devices have recently attracted significant research. However, the temporal characteristic of SNNs causes high latency, high bandwidth and high energy consumption for the…
This work proposed kernel selection approaches for probabilistic classifiers based on features produced by the convolutional encoder of a variational autoencoder. Particularly, the developed methodologies allow the selection of the most…
Photonic computing, with potentials of high parallelism, low latency and high energy efficiency, have gained progressive interest at the forefront of neural network (NN) accelerators. However, most existing photonic computing accelerators…