On-device training of machine learning models on microcontrollers with federated learning
N Llisterri Giménez, M Monfort Grau… - Electronics, 2022 - mdpi.com
Recent progress in machine learning frameworks has made it possible to now perform
inference with models using cheap, tiny microcontrollers. Training of machine learning …
inference with models using cheap, tiny microcontrollers. Training of machine learning …
Automated log-scale quantization for low-cost deep neural networks
Quantization plays an important role in deep neural network (DNN) hardware. In particular,
logarithmic quantization has multiple advantages for DNN hardware implementations, and …
logarithmic quantization has multiple advantages for DNN hardware implementations, and …
A hardware-friendly low-bit power-of-two quantization method for cnns and its fpga implementation
X Sui, Q Lv, Y Bai, B Zhu, L Zhi, Y Yang, Z Tan - Sensors, 2022 - mdpi.com
To address the problems of convolutional neural networks (CNNs) consuming more
hardware resources (such as DSPs and RAMs on FPGAs) and their accuracy, efficiency …
hardware resources (such as DSPs and RAMs on FPGAs) and their accuracy, efficiency …
Image-captioning model compression
V Atliha, D Šešok - Applied Sciences, 2022 - mdpi.com
Image captioning is a very important task, which is on the edge between natural language
processing (NLP) and computer vision (CV). The current quality of the captioning models …
processing (NLP) and computer vision (CV). The current quality of the captioning models …
Hardware-centric automl for mixed-precision quantization
Abstract Model quantization is a widely used technique to compress and accelerate deep
neural network (DNN) inference. Emergent DNN hardware accelerators begin to support …
neural network (DNN) inference. Emergent DNN hardware accelerators begin to support …
Integer-only cnns with 4 bit weights and bit-shift quantization scales at full-precision accuracy
Quantization of neural networks has been one of the most popular techniques to compress
models for embedded (IoT) hardware platforms with highly constrained latency, storage …
models for embedded (IoT) hardware platforms with highly constrained latency, storage …
Neuron-by-Neuron Quantization for Efficient Low-Bit QNN Training
Quantized neural networks (QNNs) are widely used to achieve computationally efficient
solutions to recognition problems. Overall, eight-bit QNNs have almost the same accuracy …
solutions to recognition problems. Overall, eight-bit QNNs have almost the same accuracy …
Ax-BxP: Approximate blocked computation for precision-reconfigurable deep neural network acceleration
Precision scaling has emerged as a popular technique to optimize the compute and storage
requirements of Deep Neural Networks (DNNs). Efforts toward creating ultra-low-precision …
requirements of Deep Neural Networks (DNNs). Efforts toward creating ultra-low-precision …
Adaptive Global Power-of-Two Ternary Quantization Algorithm Based on Unfixed Boundary Thresholds
X Sui, Q Lv, C Ke, M Li, M Zhuang, H Yu, Z Tan - Sensors, 2023 - mdpi.com
In the field of edge computing, quantizing convolutional neural networks (CNNs) using
extremely low bit widths can significantly alleviate the associated storage and computational …
extremely low bit widths can significantly alleviate the associated storage and computational …
Quantized Graph Neural Networks for Image Classification
X Xu, L Ma, T Zeng, Q Huang - Mathematics, 2023 - mdpi.com
Researchers have resorted to model quantization to compress and accelerate graph neural
networks (GNNs). Nevertheless, several challenges remain:(1) quantization functions …
networks (GNNs). Nevertheless, several challenges remain:(1) quantization functions …