The whitepaper offers a comprehensive overview defining the "Smart Edge AI approach" for building IoT sensing applications and explains the many benefits of creating intelligent endpoints. It then discusses automated machine learning workflows - known as "AutoML" - and reviews the key stages of the development process from modeling to prototyping.
Most importantly, says the company, the paper also gives developers new to AI and machine learning practical guidance and examples for implementing designs using such AutoML tools, which enable algorithm code to be automatically created by software that learns by example without explicit coding or data science expertise. Further, says the company, state of the art tools such as its own can build sophisticated sensor code capable of running locally on microcontrollers embedded within the IoT devices themselves.
This approach enables developers of smart edge IoT devices to build applications with real-time responsiveness, adaptive smart devices, network efficiency and resiliency, and security and data privacy, without requiring extensive data science and firmware coding expertise. The whitepaper, says the company, discusses the various items IoT developers should consider when implementing automated machine learning and provides them with practical advice from sensor selection and data capture to generating local insights.
The key sections of the whitepaper include the following:
- How the Smart Edge AI Approach Works
- The Key Stages of Implementing the Smart Edge AI Process
- Developing Your Application Model
- Prototype IoT Selection
- Sensor Selection and Data Collection
- Data Labeling
- ML Algorithm Development
- Converting an Algorithm to Optimized Endpoint Code
- Test/Validation of Local IoT Device Insight
For more, see the whitepaper: " Building Smart IoT Devices with AutoML: A Practical Guide to Zero-Coding Algorithm Design ."