Year: 2025

Implementing Weakly Supervised Human Localization with ESP32

by
Implementing Weakly Supervised Human Localization with ESP32

1. Introduction Weakly Supervised Object Localization is used to discover the location of target objects within images. Traditional object detection methods typically require precise bounding box annotations for each training sample, which can be time-consuming and labor-intensive for large-scale datasets. To address this issue, weakly supervised object localization solves the problem by using simpler annotation … Read more

Implementing Offline Command Recognition with TFLite Micro on ESP32

by
Implementing Offline Command Recognition with TFLite Micro on ESP32

1. Introduction Voice recognition, as an important method of human-computer interaction, is gradually becoming one of the core functions of smart devices. However, traditional voice recognition systems often rely on cloud servers for audio data processing and analysis, which brings issues such as latency and privacy. TensorFlow Lite provides an efficient and fast solution for … Read more

Efficient LLM Inference with Block Sparse Attention

by
Efficient LLM Inference with Block Sparse Attention

Click the card below to follow the “LiteAI” public account Hi, everyone, I am Lite. A while ago, I shared the Efficient Large Model Full-Stack Technology from Part 1 to Part 19, which includes content on large model quantization and fine-tuning, efficient LLM inference, quantum computing, generative AI acceleration, etc. The content links are as … Read more

The Role of TinyML in the Industry

by
The Role of TinyML in the Industry

Editor’s Note: The author, Jose Vicente Sáez Ibáñez, is a senior ML and software development engineer with international experience. He has been dedicated to researching the intersection of artificial intelligence and the Internet of Things (AIoT). Over the past few years, he has been deeply involved in the smart city industry across China, Spain, and … Read more

Getting Started with TinyML Voice Recognition Using Zilltek Microphone

by
Getting Started with TinyML Voice Recognition Using Zilltek Microphone

Click the blue text to follow us Introduction In today’s Internet of Things era, the application of voice recognition technology is becoming increasingly widespread. This article will introduce how to deploy a TinyML voice recognition system and detail the process from data collection to model deployment. Getting Started with TinyML: Implementing TinyML Voice Recognition Using … Read more

Learning TinyML From Scratch: Optimization Techniques

by
Learning TinyML From Scratch: Optimization Techniques

This article is contributed by the community, author Wang Yucheng, ML&IoT Google Developers Expert, Chief Engineer of the Intelligent Lock Research Institute at Wenzhou University. Learn more: https://blog.csdn.net/wfing After discussing the previous chapters, we have understood the concept of TinyML, completed the simplest TinyML model and ran it on a microcontroller, yielding the most basic … Read more

How to Implement TinyML? A Review of Efficient Neural Networks for Micro Machine Learning

by
How to Implement TinyML? A Review of Efficient Neural Networks for Micro Machine Learning

Tiny Machine Learning (TinyML) has gained significant attention due to its potential to enable intelligent applications on resource-constrained devices. This review provides an in-depth analysis of the advancements in efficient neural networks and the deployment methods of deep learning models for TinyML applications on ultra-low-power microcontrollers (MCUs). It first introduces neural networks along with their … Read more

Understanding tinyML: Machine Learning on MCUs

by
Understanding tinyML: Machine Learning on MCUs

Author: C. J. Abate (USA) Translator: Jun Qian Machine Learning (ML), as a subset of Artificial Intelligence, has been widely applied in various fields, including atmospheric science and computer vision. As Harvard PhD Matthew Stewart states, tinyML is an emerging discipline that enables low-resource, low-power machine learning algorithms to run on resource-constrained microcontrollers. C.J. Abate: … Read more

Overview of TinyML: Progress and Future by MIT’s Han Song

by
Overview of TinyML: Progress and Future by MIT's Han Song

Tiny Machine Learning (TinyML) is the new frontier of machine learning. By compressing deep learning models into billions of Internet of Things (IoT) devices and microcontrollers (MCUs), we expand the scope of AI applications and achieve ubiquitous intelligence. However, due to hardware limitations, TinyML faces challenges: the tiny memory resources make it difficult to accommodate … Read more

Advancing Edge AI with TinyML

by
Advancing Edge AI with TinyML

We previously published an article titled “TinyML: The Next Wave of Artificial Intelligence Revolution“, and held several events related to machine learning. We believe everyone has a certain understanding of TinyML, so why did we choose TinyML? Why Choose TinyML? ✦ Artificial Intelligence (AI) is rapidly transitioning from the cloud to the edge, entering increasingly … Read more