Hardware/software co-design for tinyml voice-recognition application on resource frugal Edge Devices
On-device artificial intelligence has attracted attention globally, and attempts to combine the
internet of things and TinyML (machine learning) applications are increasing. Although most …
internet of things and TinyML (machine learning) applications are increasing. Although most …
Automatic deployment of convolutional neural networks on fpga for spaceborne remote sensing application
In recent years, convolutional neural network (CNN)-based algorithms have been widely
used in remote sensing image processing and show tremendous performance in a variety of …
used in remote sensing image processing and show tremendous performance in a variety of …
[PDF][PDF] Binary and multi-class assessment of face mask classification on edge AI using CNN and transfer learning
This paper empirically studies the impact of Sigmoid activation function in binary cross-
entropy loss against softmax in categorical cross-entropy loss for binary classification …
entropy loss against softmax in categorical cross-entropy loss for binary classification …
A TensorFlow extension framework for optimized generation of hardware CNN inference engines
The workloads of Convolutional Neural Networks (CNNs) exhibit a streaming nature that
makes them attractive for reconfigurable architectures such as the Field-Programmable Gate …
makes them attractive for reconfigurable architectures such as the Field-Programmable Gate …
MAFIA: Machine learning acceleration on FPGAs for IoT applications
NP Ghanathe, V Seshadri, R Sharma… - … Conference on Field …, 2021 - ieeexplore.ieee.org
Recent breakthroughs in ML have produced new classes of models that allow ML inference
to run directly on milliwatt-powered IoT devices. On one hand, existing ML-to-FPGA …
to run directly on milliwatt-powered IoT devices. On one hand, existing ML-to-FPGA …
From Circuits to SoC Processors: Arithmetic Approximation Techniques & Embedded Computing Methodologies for DSP Acceleration
V Leon - arXiv preprint arXiv:2302.12194, 2023 - arxiv.org
The computing industry is forced to find alternative design approaches and computing
platforms to sustain increased power efficiency, while providing sufficient performance …
platforms to sustain increased power efficiency, while providing sufficient performance …
A novel automate python edge-to-edge: From automated generation on cloud to user application deployment on edge of deep neural networks for low power IoT …
Deep Neural Networks (DNNs) deployment for IoT Edge applications requires strong skills
in hardware and software. In this paper, a novel design framework fully automated for Edge …
in hardware and software. In this paper, a novel design framework fully automated for Edge …
A performance characterization of AI algorithms on energy-efficient hardware with applications to robust autonomous landing
A Gracia-Berná, M Hardt, AF Rodríguez… - 2023 IEEE/AIAA …, 2023 - ieeexplore.ieee.org
Artificial Intelligence (AI) is penetrating industries on many levels, and a European wide
project consisting of the main industrial leaders are working on new chip architectures and …
project consisting of the main industrial leaders are working on new chip architectures and …
Platform generation for edge AI devices with custom hardware accelerators
In recent years artificial neural networks (NNs) have been at the center of research on data
processing. However, their high computational demand often prohibits deployment on …
processing. However, their high computational demand often prohibits deployment on …
An Optimal Design Method of Conv2d Operator for TensorFlow Based on FPGA Accelerator
R Li, H Kan, D Su, Y Wang, H Zhao… - Proceedings of the 4th …, 2020 - dl.acm.org
Currently, TensorFlow architecture only supports CPU and GPU programming, and has not
yet formed a unified support standard for FPGAs. To the best of our knowledge, when …
yet formed a unified support standard for FPGAs. To the best of our knowledge, when …