Deep Learning Techniques for Security in Edge Computing: A Detailed Survey
Massive amounts of data are generated instantly and as computing power gets increased
subsequently the performance of cloud computing is dissatisfying. The security and privacy …
subsequently the performance of cloud computing is dissatisfying. The security and privacy …
Budget-Aware Pruning for Multi-Domain Learning
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 …
FAQ: Mitigating the Impact of Faults in the Weight Memory of DNN Accelerators through Fault-Aware Quantization
MA Hanif, M Shafique - 2023 International Joint Conference on …, 2023 - ieeexplore.ieee.org
Permanent faults induced due to imperfections in the manufacturing process of Deep Neural
Network (DNN) accelerators are a major concern, as they negatively impact the …
Network (DNN) accelerators are a major concern, as they negatively impact the …
Mosaics, The Best of Both Worlds: Analog devices with Digital Spiking Communication to build a Hybrid Neural Network Accelerator
Neuromorphic architectures have seen a resurgence of interest in the past decade owing to
100x-1000x efficiency gain over conventional Von Neumann architectures. Digital …
100x-1000x efficiency gain over conventional Von Neumann architectures. Digital …
Budget-Aware Pruning for Multi-domain Learning
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 …
A fast design space exploration framework for the deep learning accelerators: Work-in-progress
The Capsule Networks (CapsNets) is an advanced form of Convolutional Neural Network
(CNN), capable of learning spatial relations and being invariant to transformations …
(CNN), capable of learning spatial relations and being invariant to transformations …
Model Compression for Resource-Constrained Mobile Robots
T Souroulla, A Hata, A Terra, Ö Özkahraman… - arXiv preprint arXiv …, 2022 - arxiv.org
The number of mobile robots with constrained computing resources that need to execute
complex machine learning models has been increasing during the past decade. Commonly …
complex machine learning models has been increasing during the past decade. Commonly …
Co-optimization of neural networks and hardware architectures for their efficient execution
CID Latotzke, D Stroobandt, T Gemmeke - 2024 - publications.rwth-aachen.de
Kurzfassung Im Folgenden werden die Motivation, das Ziel und die Aufgabe der Dissertation
beschrieben. Der herausragende Sieg von AlexNet bei der ImageNet Large Scale …
beschrieben. Der herausragende Sieg von AlexNet bei der ImageNet Large Scale …
A Statistical Approach to Stochastic Computing Design and Analysis
T Baker - 2023 - deepblue.lib.umich.edu
Stochastic computing (SC) is an unconventional computing style that uses probabilistic
bitstreams to implement algorithms like those for machine learning, digital filtering, and …
bitstreams to implement algorithms like those for machine learning, digital filtering, and …
[PDF][PDF] Energy-Efficient Inference on the Edge Exploiting TinyML Capabilities for UAVs. Drones 2021, 5, 127
In recent years, the proliferation of unmanned aerial vehicles (UAVs) has increased
dramatically. UAVs can accomplish complex or dangerous tasks in a reliable and cost …
dramatically. UAVs can accomplish complex or dangerous tasks in a reliable and cost …