• Hardware
• Software
• Other Interesting Resources
• My Experience with Edge AI

• OpenMV - A camera that runs with MicroPython on ARM Cortex M6/M7 and great support for computer vision algorithms. Now with support for Tensorflow Lite too.
• JeVois - A TensorFlow-enabled camera module.
• Edge TPU - Google’s purpose-built ASIC designed to run inference at the edge.
• Movidius - Intel's family of SoCs designed specifically for low power on-device computer vision and neural network applications.
  • UP AI Edge - Line of products based on Intel Movidius VPUs (including Myriad 2 and Myriad X) and Intel Cyclone FPGAs.
  • DepthAI - An embedded platform for combining Depth and AI, built around Myriad X
• NVIDIA Jetson - High-performance embedded system-on-module to unlock deep learning, computer vision, GPU computing, and graphics in network-constrained environments.
  • Jetson TX1
  • Jetson TX2
  • Jetson Nano
• Artificial Intelligence Radio - Transceiver (AIR-T) - High-performance SDR seamlessly integrated with state-of-the-art deep learning hardware.
• Kendryte K210 - Dual-core, RISC-V chip with convolutional neural network acceleration using 64 KLUs (Kendryte Arithmetic Logic Unit).
  • Sipeed M1 - Based on the Kendryte K210, the module adds WiFi connectivity and an external flash memory.
  • M5StickV - AIoT(AI+IoT) Camera powered by Kendryte K210
  • UNIT-V - AI Camera powered by Kendryte K210 (lower-end M5StickV)
• Kendryte K510 - Tri-core RISC-V processor clocked with AI accelerators.
• GreenWaves GAP8 - RISC-V-based chip with hardware acceleration for convolutional operations.
• Ultra96 - Embedded development platform featuring a Xilinx UltraScale+ MPSoC FPGA.
• Apollo3 Blue - SparkFun Edge Development Board powered by a Cortex M4 from Ambiq Micro.
• Google Coral - Platform of hardware components and software tools for local AI products based on Google Edge TPU coprocessor.
  • Dev boards
  • USB Accelerators
  • PCIe / M.2 modules
• Gyrfalcon Technology Lighspeeur - Family of chips optimized for edge computing.
• ARM microNPU - Processors designed to accelerate ML inference (being the first one the Ethos-U55).
• Espressif ESP32-S3 - SoC similar to the well-known ESP32 with support for AI acceleration (among many other interesting differences).
• Maxim MAX78000 - SoC based on a Cortex-M4 that includes a CNN accelerator.
• Beagleboard BeagleV - Open Source RISC-V-based Linux board that includes a Neural Network Engine.
• Syntiant TinyML - Development kit based on the Syntiant NDP101 Neural Decision Processor and a SAMD21 Cortex-M0+.

• TensorFlow Lite - Lightweight solution for mobile and embedded devices which enables on-device machine learning inference with low latency and a small binary size.
• TensorFlow Lite for Microcontrollers - Port of TF Lite for microcontrollers and other devices with only kilobytes of memory. Born from a merge with uTensor.
• Embedded Learning Library (ELL) - Microsoft's library to deploy intelligent machine-learned models onto resource constrained platforms and small single-board computers.
• uTensor - AI inference library based on mbed (an RTOS for ARM chipsets) and TensorFlow.
• CMSIS NN - A collection of efficient neural network kernels developed to maximize the performance and minimize the memory footprint of neural networks on Cortex-M processor cores.
• ARM Compute Library - Set of optimized functions for image processing, computer vision, and machine learning.
• Qualcomm Neural Processing SDK for AI - Libraries to developers run NN models on Snapdragon mobile platforms taking advantage of the CPU, GPU and/or DSP.
• ST X-CUBE-AI - Toolkit for generating NN optimiezed for STM32 MCUs.
• ST NanoEdgeAIStudio - Tool that generates a model to be loaded into an STM32 MCU.
• Neural Network on Microcontroller (NNoM) - Higher-level layer-based Neural Network library specifically for microcontrollers. Support for CMSIS-NN.
• nncase - Open deep learning compiler stack for Kendryte K210 AI accelerator.
• deepC - Deep learning compiler and inference framework targeted to embedded platform.
• uTVM - MicroTVM is an open source tool to optimize tensor programs.
• Edge Impulse - Interactive platform to generate models that can run in microcontrollers. They are also quite active on social netwoks talking about recent news on EdgeAI/TinyML.
• Qeexo AutoML - Interactive platform to generate AI models targetted to microcontrollers.
• mlpack - C++ header-only fast machine learning library that focuses on lightweight deployment. It has a wide variety of machine learning algorithms with the possibility to realize on-device learning on MPUs.
• AIfES - platform-independent and standalone AI software framework optimized for embedded systems.
• onnx2c - ONNX to C compiler targeting "Tiny ML".

• Benchmarking Edge Computing (May 2019)
• Hardware benchmark for edge AI on cubesats - Open Source Cubesat Workshop 2018
• Why Machine Learning on The Edge?
• Tutorial: Low Power Deep Learning on the OpenMV Cam
• TinyML: Machine Learning with TensorFlow on Arduino and Ultra-Low Power Micro-Controllers - O'Reilly book written by Pete Warden, Daniel Situnayake.
• tinyML Summit - Annual conference and monthly meetup celebrated in California, USA. Talks and slides are usually available from the website.
• TinyML Papers and Projects - Compilation of the most recent paper's and projects in the TinyML/EdgeAI field.
• MinUn - Accurate ML Inference on Microcontrollers.

Throughout my career as a Senior Firmware Engineer, I have immersed myself in Edge AI, working on innovative projects that leverage artificial intelligence at the edge of networks. My journey began with a strong foundation in ARM-based development, where I honed my skills on platforms like Qualcomm, NXP, and Rockchip.

I have successfully developed AI-driven IoT devices using NVIDIA Jetson, CUDA, and TensorRT, enabling advanced functionalities in real-time applications. My expertise in various connectivity solutions, including BLE, LoRa, LTE, and NB-IoT, has allowed me to create seamless communication between devices, enhancing their overall performance.

Working with TinyML, Raspberry Pi, and frameworks like Zephyr and FreeRTOS, I have implemented robust testing methodologies that ensure reliability and efficiency in my projects. This hands-on experience has not only deepened my technical skills but also fostered a passion for pushing the boundaries of what’s possible in Edge AI.

Advice for New Edge AI Enthusiasts

1. Start with the Basics: Familiarize yourself with fundamental concepts in AI and IoT. Understanding how these technologies interact is crucial.

2. Hands-On Practice: Engage in projects that allow you to apply your knowledge. Platforms like Raspberry Pi and NVIDIA Jetson are great for experimentation.

3. Learn Programming Languages: Proficiency in languages like C/C++, Python, and Rust will be invaluable. Focus on mastering one language before expanding your skill set.

4. Explore Connectivity Solutions: Understanding various connectivity protocols (BLE, LoRa, etc.) is essential for creating effective Edge AI solutions.

5. Join Communities: Connect with other enthusiasts and professionals through forums, online courses, and local meetups. Sharing knowledge and experiences can accelerate your learning.

6. Stay Updated: The field of Edge AI is rapidly evolving. Follow industry news, research papers, and attend webinars to keep your skills current.

7. Embrace Challenges: Don’t be afraid to tackle complex problems. Each challenge you face is an opportunity to learn and grow.

By following these steps and maintaining a curious mindset, new enthusiasts can thrive in the exciting field of Edge AI.