FasTrCaps: An integrated framework for fast yet accurate training of capsule networks
Recently, Capsule Networks (CapsNets) have shown improved performance compared to
the traditional Convolutional Neural Networks (CNNs), by encoding and preserving spatial …
the traditional Convolutional Neural Networks (CNNs), by encoding and preserving spatial …
Deep learning applications on edge computing
NK Trivedi, A Anand, UK Lilhore… - Machine Learning for …, 2022 - taylorfrancis.com
In various applications, such as computer vision and natural language processing, deep
learning is commonly used. End devices like smartphones and sensors on the Internet of …
learning is commonly used. End devices like smartphones and sensors on the Internet of …
Enabling pervasive federated learning using vehicular virtual edge servers
Recent works have proposed various distributed federated learning (FL) systems for the
edge computing paradigm. These FL algorithms can assist pervasive applications in various …
edge computing paradigm. These FL algorithms can assist pervasive applications in various …
State-of-the-art techniques in deep edge intelligence
The potential held by the gargantuan volumes of data being generated across networks
worldwide has been truly unlocked by machine learning techniques and more recently Deep …
worldwide has been truly unlocked by machine learning techniques and more recently Deep …
Multiplexer-majority chains: Managing correlation and cost in stochastic number generation
High-cost stochastic number generators (SNGs) are the main source of stochastic numbers
(SNs) in stochastic computing. Interacting SNs must usually be uncorrelated for satisfactory …
(SNs) in stochastic computing. Interacting SNs must usually be uncorrelated for satisfactory …
Budget-Aware Pruning: Handling Multiple Domains with Less Parameters
Deep learning has achieved state-of-the-art performance on several computer vision tasks
and domains. Nevertheless, it still has a high computational cost and demands a significant …
and domains. Nevertheless, it still has a high computational cost and demands a significant …
Labani: Layer-based noise injection attack on convolutional neural networks
Hardware accelerator-based CNN inference improves the performance and latency but
increases the time-to-market. As a result, CNN deployment on hardware is often outsourced …
increases the time-to-market. As a result, CNN deployment on hardware is often outsourced …
Exploiting resiliency for kernel-wise cnn approximation enabled by adaptive hardware design
C De la Parra, A El-Yamany, T Soliman… - … on Circuits and …, 2021 - ieeexplore.ieee.org
Efficient low-power accelerators for Convolutional Neural Networks (CNNs) largely benefit
from quantization and approximation, which are typically applied layer-wise for efficient …
from quantization and approximation, which are typically applied layer-wise for efficient …
Hardware and Software Optimizations for Capsule Networks
Abstract Among advanced Deep Neural Network models, Capsule Networks (CapsNets)
have shown high learning and generalization capabilities for advanced tasks. Their …
have shown high learning and generalization capabilities for advanced tasks. Their …
Edge Computing for IoT
Over the past few years, the idea of edge computing has seen substantial expansion in both
academic and industrial circles. This computing approach has garnered attention due to its …
academic and industrial circles. This computing approach has garnered attention due to its …