Review of lightweight deep convolutional neural networks
F Chen, S Li, J Han, F Ren, Z Yang - Archives of Computational Methods …, 2024 - Springer
Lightweight deep convolutional neural networks (LDCNNs) are vital components of mobile
intelligence, particularly in mobile vision. Although various heavy networks with increasingly …
intelligence, particularly in mobile vision. Although various heavy networks with increasingly …
Photonic reconfigurable accelerators for efficient inference of cnns with mixed-sized tensors
SS Vatsavai, IG Thakkar - IEEE Transactions on Computer …, 2022 - ieeexplore.ieee.org
Photonic microring resonator (MRR)-based hardware accelerators have been shown to
provide disruptive speedup and energy-efficiency improvements for processing deep …
provide disruptive speedup and energy-efficiency improvements for processing deep …
Sconna: A stochastic computing based optical accelerator for ultra-fast, energy-efficient inference of integer-quantized cnns
Convolutional Neural Networks (CNNs) are used extensively for artificial intelligence
applications due to their record-breaking accuracy. For efficient and swift hardware-based …
applications due to their record-breaking accuracy. For efficient and swift hardware-based …
Neural network training with limited precision and asymmetric exponent
M Pietrołaj, M Blok - Journal of Big Data, 2022 - Springer
Along with an extremely increasing number of mobile devices, sensors and other smart
utilities, an unprecedented growth of data can be observed in today's world. In order to …
utilities, an unprecedented growth of data can be observed in today's world. In order to …
Designing Deep Learning Models on FPGA with Multiple Heterogeneous Engines
Deep learning models are becoming more complex and heterogeneous with new layer
types to improve their accuracy. This brings a considerable challenge to the designers of …
types to improve their accuracy. This brings a considerable challenge to the designers of …
Toward Energy-Efficient Massive MIMO: Graph Neural Network Precoding for Mitigating Non-Linear PA Distortion
Massive MIMO systems are typically designed assuming linear power amplifiers (PAs).
However, PAs are most energy efficient close to saturation, where non-linear distortion …
However, PAs are most energy efficient close to saturation, where non-linear distortion …
A Comparative Analysis of Microrings Based Incoherent Photonic GEMM Accelerators
Several analog photonic architectures based on microring resonators (MRRs) have been
proposed to accelerate general matrix-matrix multiplications (GEMMs) that compose deep …
proposed to accelerate general matrix-matrix multiplications (GEMMs) that compose deep …
A Low-Dissipation and Scalable GEMM Accelerator with Silicon Nitride Photonics
Over the past few years, several microring resonator (MRR)-based analog photonic
architectures have been proposed to accelerate general matrix-matrix multiplications …
architectures have been proposed to accelerate general matrix-matrix multiplications …
Edge AI–A Promising Technology
Summary Edge Artificial Intelligence (Edge AI) has become the buzzword for every industry
organization. Edge intelligence utilizes edge computing to access and analyze the data from …
organization. Edge intelligence utilizes edge computing to access and analyze the data from …
Нейроморфные системы: приборы, архитектура и алгоритмы
КА Фетисенкова, АЕ Рогожин - Mikroèlektronika, 2023 - journals.rcsi.science
Применение структуры и принципов работы человеческого мозга открывает большие
возможности для создания искусственных систем на основе кремниевой технологии …
возможности для создания искусственных систем на основе кремниевой технологии …