Optimization of through‐time radial GRAPPA with coil compression and weight sharing
Sign Up to like & getrecommendations! Published in 2022 at "Magnetic Resonance in Medicine"
DOI: 10.1002/mrm.29258
Abstract: This work proposes principal component analysis (PCA) coil compression and weight sharing to reduce acquisition and reconstruction time of through‐time radial GRAPPA. read more here.
Keywords: compression weight; time; radial grappa; coil compression ... See more keywords
Accelerating Deep Neural Networks for Efficient Scene Understanding in Multi-Modal Automotive Applications
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Access"
DOI: 10.1109/access.2023.3258400
Abstract: Environment perception constitutes one of the most critical operations performed by semi- and fully- autonomous vehicles. In recent years, Deep Neural Networks (DNNs) have become the standard tool for perception solutions owing to their impressive… read more here.
Keywords: neural networks; deep neural; multi modal; weight sharing ... See more keywords
A 8.81 TFLOPS/W Deep-Reinforcement-Learning Accelerator With Delta-Based Weight Sharing and Block-Mantissa Reconfigurable PE Array
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Circuits and Systems II: Express Briefs"
DOI: 10.1109/tcsii.2024.3374725
Abstract: TD3 is one of the most high-performing Deep Reinforcement Learning (DRL) algorithms, providing high training stability and rewards. However, it suffers from low energy efficiency due to high External Memory Access (EMA) and floating point… read more here.
Keywords: block mantissa; based weight; weight sharing; reinforcement learning ... See more keywords
Exploring Conflict-Matching Learning With Temporal Weight-Sharing and Bandwise Spatial-Interacting Transformer for Hyperspectral Change Detection
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Geoscience and Remote Sensing"
DOI: 10.1109/tgrs.2024.3465537
Abstract: Hyperspectral imagery is valuable for accurate detection of land-cover changes within a consistent area across time. However, current training paradigms for hyperspectral change detection (CD) are usually in supervised form which are not consistent to… read more here.
Keywords: bandwise spatial; change detection; conflict; weight sharing ... See more keywords
PWSNAS: Powering Weight Sharing NAS With General Search Space Shrinking Framework.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3156373
Abstract: Neural architecture search (NAS) depends heavily on an efficient and accurate performance estimator. To speed up the evaluation process, recent advances, like differentiable architecture search (DARTS) and One-Shot approaches, instead of training every model from… read more here.
Keywords: weight sharing; sharing nas; search space; powering weight ... See more keywords
Comparison of low-complexity sparse and weight-sharing nonlinear equalizers for C-band 100-Gbit/s DSB PAM-4 transmission over 60-km SSMF.
Sign Up to like & getrecommendations! Published in 2022 at "Optics express"
DOI: 10.1364/oe.468635
Abstract: To cope with the nonlinear distortions and the chromatic dispersion (CD) induced power fading in double-side band (DSB) intensity modulation and direct detection (IM/DD) transmission systems, high-performance Volterra nonlinear equalizers (VNLEs) including Volterra feed-forward equalizer… read more here.
Keywords: low complexity; performance; transmission; vdfe ... See more keywords
C-band 100-GBaud/λ PAM-4 transmission enabled by hardware-efficient nonlinear equalizer with weight-sharing pruning.
Sign Up to like & getrecommendations! Published in 2022 at "Optics letters"
DOI: 10.1364/ol.477320
Abstract: A Volterra nonlinear equalizer (VNLE) can effectively mitigate both linear and nonlinear impairments arising in intensity-modulation direct-detection (IM-DD) transmission systems. However, the high computational complexity of the VNLE hinders its applications. Here, we propose a… read more here.
Keywords: equalizer; nonlinear equalizer; equalizer weight; transmission ... See more keywords