Recently, at the Entropy Technology Partner Conference 2025 held in Hangzhou, Entropy Technologyreleased the world’s first “BioCV TinyML Multimodal Model Technology Application White Paper”. This white paper not only encapsulates the wisdom and efforts of the Entropy Technology R&D team but also marks a significant technological breakthrough in edge AI model optimization and low-power computing, … Read more
Recently, the news of STMicroelectronics’ (ST) acquisition of the Canadian AI startup Deeplite has attracted industry attention.Deeplite claims to be the DeepSeek of edge AI, with unique technologies in model optimization, quantization, and compression that enable AI large models to run faster, smaller, and more energy-efficiently on edge devices. Since DeepSeek popularized distilled models, more … Read more
Intelligence is getting closer to us, not just “nearby”, butface-to-face that close. The smart watch on your wrist, the robotic vacuum cleaner, or even a surveillance camera may be running a lightweight AI model behind the scenes. No longer should we think that AI can only exist in the cloud, relying on powerful GPUs; it … Read more
According to a report by Electronic Enthusiasts (Author: Wu Zipeng), when developing humanoid robot solutions, most people equate the intelligence capabilities of robots with AI large models. With high-performance AI chips paired with AI large models, the intelligence level of humanoid robots has significantly improved. However, AI large models are primarily used for high-level intelligent … Read more
ArduTFLite——Arduino-style TensorFlow Lite Micro library ArduTFLite library simplifies the use of TensorFlow Lite Micro on Arduino boards, providing a typical Arduino-style API. It avoids the use of pointers or other C++ syntax structures that are discouraged in Arduino sketches. ArduTFLite serves as a wrapper for the Chirale_TensorFlowLite library, which is a port of the official … Read more
Author: Sophia IoT Think Tank Original As generative artificial intelligence stirs a global technological wave, another, more “low-key” yet equally critical technological direction is quietly rising: Edge AI, or as it is popularly known this year, On-Device AI. If Edge AI focuses on the decentralization of computing resources, then On-Device AI primarily involves the direct … Read more
Hey, recently I’ve been tinkering with something fun — running machine learning on those tiny IoT devices! Seeing the number “1KB”, many people shake their heads: how is that possible? Indeed, a high-definition photo takes several MB, so where’s the magic that allows AI to fit into such a tiny space? Actually, TinyML is such … Read more
In recent years, artificial intelligence technology has developed rapidly, but its powerful computing capabilities often rely on cloud servers. This poses a significant challenge for resource-constrained embedded devices. However, the rise of TinyML (Tiny Machine Learning) technology brings new hope: enabling resource-limited microcontrollers to run deep learning models! This article will take you into the … Read more
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
Edge AI: Three Memory Compression Techniques for Deploying TinyML with MicroPython To be honest, when I first tried to run a neural network on the ESP32, I was almost driven to madness. 256KB of RAM? Are you serious? That 5MB model I trained on Colab was completely out of the question. However, after experimenting over … Read more