Conference Invitation Artificial Intelligence (AI) Chip Design Seminar (July 25, Beijing National Convention Center) A domestic startup specializing in AI FPGA acceleration algorithms, Deep Insight Technology, was acquired by the international giant Xilinx just two days ago, causing quite a stir in the industry. Currently, there are quite a number of companies in China working … Read more
[Image] We can optimize the neural network architecture to fit within the memory and computational constraints of microcontrollers without compromising accuracy. In this article, we will explain and explore the potential of depthwise separable convolutional neural networks for implementing keyword recognition on Cortex-M processors. Keyword recognition (KWS) is crucial for enabling voice-based user interaction on … Read more
Introduction The rapid development of artificial intelligence technology has led to the widespread application of intelligent voice embedded systems based on neural network technology in industries such as smartphones, smart speakers, wearable devices, smart homes, AI IoT, robotics, and automotive assistance systems due to their small size, low power consumption, and low cost. This article … Read more
Professors Ma Chunyuan and Zhang Tao from Northwestern Polytechnical University, along with masters Chen Jing and Yao Ding, recently published a paper titled “Evaluation Methods for Computing Power of Embedded Intelligent Computers” in the Journal of Computer Science. The abstract of the paper is as follows. Scan the QR code or click “Read the original … Read more
CMSIS_NN Overview Paper Title: “CMSIS-NN: Efficient Neural Network Kernels for Arm Cortex-M CPUs”, 2018 Organization: ARM 0. Introduction CMSIS-NN is a neural network inference library for ARM Cortex-M series chips, designed for deploying neural networks on low-performance chips/architectures. 1. Convolution and Matrix Multiplication Using the 16-bit multiply-accumulate SIMD instruction, SMLAD. 1.1 __SXTB16 Data Extension Most … Read more
For some time now, I have been contemplating setting up an environment to implement algorithms based on neural networks on a smaller (8-pin) microcontroller. After reviewing existing solutions, I found that none truly satisfied me. An obvious problem is that flexibility often comes at the cost of overhead. As usual, for a truly optimized solution, … Read more