paper-with-me

Papers

Poor Man's Training on MCUs: A Memory-Efficient Quantized Back-Propagation-Free Approach

2024-11-07 · Yequan Zhao, Hai Li, Ian Young, Zheng Zhang

Back propagation (BP) is the default solution for gradient computation in neural network training. However, implementing BP-based training on various edge devices such as FPGA, microcontrollers (MCUs), and analog computing platforms face multiple major challenges, such as the lack of hardware resources, long time-to-market, and dramatic errors in a low-precision setting. This paper presents a simple BP-free training scheme on an MCU, which makes edge training hardware design as easy as inference hardware design. We adopt a quantized zeroth-order method to estimate the gradients of quantized model parameters, which can overcome the error of a straight-through estimator in a low-precision BP scheme. We further employ a few dimension reduction methods (e.g., node perturbation, sparse training) to improve the convergence of zeroth-order training. Experiment results show that our BP-free training achieves comparable performance as BP-based training on adapting a pre-trained image classifier to various corrupted data on resource-constrained edge devices (e.g., an MCU with 1024-KB SRAM for dense full-model training, or an MCU with 256-KB SRAM for sparse training). This method is most suitable for application scenarios where memory cost and time-to-market are the major concerns, but longer latency can be tolerated.

📄 PDF Abstract BibTeX arXiv:2411.05873

Code (0)

등록된 구현이 없습니다.

Tasks

Dimensionality Reduction

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

On-Device Training of Fully Quantized Deep Neural Networks on Cortex-M Microcontrollers

2024-07-15 · Mark Deutel, Frank Hannig, Christopher Mutschler, Jürgen Teich

On-device training of DNNs allows models to adapt and fine-tune to newly collected data or changing domains while deployed on microcontroller units (MCUs). However, DNN training is a resource-intensive task, making the i…

Time Series

Neural Network Quantization for Microcontrollers: A Comprehensive Survey of Methods, Platforms, and Applications

2025-08-20 · Hamza A. Abushahla, Dara Varam, Ariel Justine N. Panopio, Mohamed I. AlHajri arxiv

The deployment of Quantized Neural Networks (QNNs) on resource-constrained edge devices, such as microcontrollers (MCUs), introduces fundamental challenges in balancing model performance, computational complexity, and me…

Deep Compression for PyTorch Model Deployment on Microcontrollers

2021-03-29 · Eren Dogan, H. Fatih Ugurdag, Hasan Unlu

Neural network deployment on low-cost embedded systems, hence on microcontrollers (MCUs), has recently been attracting more attention than ever. Since MCUs have limited memory capacity as well as limited compute-speed, i…

modelModel Compression

TinyProp -- Adaptive Sparse Backpropagation for Efficient TinyML On-device Learning

2023-08-17 · Marcus Rüb, Daniel Maier, Daniel Mueller-Gritschneder, Axel Sikora

Training deep neural networks using backpropagation is very memory and computationally intensive. This makes it difficult to run on-device learning or fine-tune neural networks on tiny, embedded devices such as low-power…

Decentor-V: Lightweight ML Training on Low-Power RISC-V Edge Devices

2025-09-10 · Marcelo Ribeiro, Diogo Costa, Gonçalo Moreira, Sandro Pinto 외 arxiv

Modern IoT devices increasingly rely on machine learning solutions to process data locally. However, the lack of graphics processing units (GPUs) or dedicated accelerators on most platforms makes on-device training large…

Federated Learning