Silicon-based optoelectronics for general-purpose matrix computation: a review
Conventional electronic processors, which are the mainstream and almost invincible
hardware for computation, are approaching their limits in both computational power and …
hardware for computation, are approaching their limits in both computational power and …
Long short-term memory recurrent neural network for automatic speech recognition
Automatic speech recognition (ASR) is one of the most demanding tasks in natural language
processing owing to its complexity. Recently, deep learning approaches have been …
processing owing to its complexity. Recently, deep learning approaches have been …
When neural architecture search meets hardware implementation: from hardware awareness to co-design
Neural Architecture Search (NAS), that automatically identifies the best network architecture,
is a promising technique to respond to the ever-growing demand for application-specific …
is a promising technique to respond to the ever-growing demand for application-specific …
A survey on the optimization of neural network accelerators for micro-ai on-device inference
Deep neural networks (DNNs) are being prototyped for a variety of artificial intelligence (AI)
tasks including computer vision, data analytics, robotics, etc. The efficacy of DNNs coincides …
tasks including computer vision, data analytics, robotics, etc. The efficacy of DNNs coincides …
heFFTe: Highly Efficient FFT for Exascale
Exascale computing aspires to meet the increasing demands from large scientific
applications. Software targeting exascale is typically designed for heterogeneous …
applications. Software targeting exascale is typically designed for heterogeneous …
Deep neural network for resource management in NOMA networks
Resource management plays a crucial role in improving sum rate of non-orthogonal multiple
access (NOMA) networks. However, the traditional resource management methods have …
access (NOMA) networks. However, the traditional resource management methods have …
In-depth analyses of unified virtual memory system for GPU accelerated computing
The abstraction of a shared memory space over separate CPU and GPU memory domains
has eased the burden of portability for many HPC codebases. However, users pay for the …
has eased the burden of portability for many HPC codebases. However, users pay for the …
Rnsnet: In-memory neural network acceleration using residue number system
We live in a world where technological advances are continually creating more data than
what we can deal with. Machine learning algorithms, in particular Deep Neural Networks …
what we can deal with. Machine learning algorithms, in particular Deep Neural Networks …
Winograd convolution for deep neural networks: Efficient point selection
SA Alam, A Anderson, B Barabasz… - ACM Transactions on …, 2022 - dl.acm.org
Convolutional neural networks (CNNs) have dramatically improved the accuracy of image,
video, and audio processing for tasks such as object recognition, image segmentation, and …
video, and audio processing for tasks such as object recognition, image segmentation, and …
Cohort-based federated learning services for industrial collaboration on the edge
Abstract Machine Learning (ML) is increasingly applied in industrial manufacturing, but often
performance is limited due to insufficient training data. While ML models can benefit from …
performance is limited due to insufficient training data. While ML models can benefit from …