Model Compression Articles

Edge AI and Lightweight Technologies: Reconstructing the Last Mile of Artificial Intelligence

2025-09-14 by boardor

Edge AI achieves a closed loop of data “generation-processing-decision” by bringing intelligent computing down to terminal devices, while lightweight technologies become the core means to break through the bottlenecks of computing power, power consumption, and latency. This article systematically analyzes three major technical paths: model compression, hardware acceleration, and software-hardware collaboration, validating the effectiveness of … Read more

Practical Edge AI with Python: From TinyML to NVIDIA Jetson for Edge Intelligence

2025-09-09 by boardor

1. Evolution of Edge AI Technology From TinyML microcontroller-level inference to NVIDIA Jetson GPU-accelerated computing, the edge AI technology stack achieves a balance between computing power and power consumption. This tutorial covers the entire link of model lightweighting → real-time inference → offline deployment, focusing on solving core challenges such as model compression, hardware heterogeneity, … Read more

New Breakthrough in TinyML! Efficient Indoor Localization Using Transformers and Mamba

2025-09-05 by boardor

Paper Title: Optimising TinyML with Quantization and Distillation of Transformer and Mamba Models for Indoor Localisation on Edge DevicesPublication Date: December 2024Authors: Thanaphon Suwannaphong, Ferdian Jovan, Ian Craddock, Ryan McConvilleAffiliations: University of Bristol, University of AberdeenOriginal Link: https://arxiv.org/pdf/2412.09289Open Source Code and Dataset Link: https://github.com/AloeUoB/tinyML_indoor_localisation Introduction Typically, accurate indoor localization systems rely on large machine learning … Read more

TinyMLPy: A Lightweight Deep Learning Model Library in Python

2025-07-07 by boardor

TinyMLPy is a Python library focused on the development of lightweight deep learning models, offering efficient model compression and deployment capabilities. In the field of deep learning, lightweight AI has become an important development direction, from model compression and quantization optimization to deployment on micro devices. In practical applications, TinyMLPy can help us: Compress deep … Read more

How to Deploy AI Models at the Edge?

2025-04-20 by boardor

According to reports from Electronic Enthusiasts (Written by Li Wanwan), in the era of artificial intelligence, more and more AI applications need to extend from the cloud to the edge, such as smart headphones, smart cameras, smart bracelets, logistics robots, etc. Deploying AI at the edge has become a trend. With the rapid development of … Read more