NXP boosts edge AI IoT

Noting a growing demand for artificial intelligence (AI) that can run on edge devices with microcontrollers (MCUs) and microprocessors (MPUs), NXP Semiconductors has unveiled tools to enable developers to deploy and use AI across a spectrum of edge processors.

The automotive, industrial, mobile and communications infrastructure tech firm believes that deploying AI at the edge offers several benefits, including lower latency, reduced energy consumption and enhanced data privacy. NXP’s expansion of the eIQ Toolkit is intended to make those deployments easier and faster, giving developers access to a wider range of model types, from generative AI (GenAI), to time series-based models, to vision-based models. Users can also deploy these models on a wider range of edge processors.

The company has added GenAI Flow with retrieval augmented generation (RAG) – a method to securely fine-tune models on domain-specific knowledge and private data without expensive retraining of the original model – to make GenAI applications accessible on edge devices. It has enhanced its eIQ Time Series Studio and eIQ AI and machine learning development software to make it easier to deploy and use AI across small MCUs and larger and more powerful MPUs.

The GenAI Flow will provide the building blocks for large language models (LLMs) that power GenAI solutions. Designed to be used with MPUs such as NXP’s i.MX family of applications processors, the GenAI solutions are said to make it easier to deploy intelligence at the edge by training large language models (LLMs) on specific contextual data.

For example, an appliance equipped with an LLM trained on the user manual could converse with a user in natural language about how to access features, perform tasks, or otherwise optimise usage and maintenance.

The eIQ Time Series Studio is designed to simplify and accelerate development and deployment for time series-based AI models. Example applications and use cases include anomaly detection such as detecting water flow/leaks and monitoring temperature; predictive maintenance for the likes of machine health and operation modes, and acoustic events like smoke alarms; regression with energy demand forecasting and building temperature control optimisation.

The eIQ Time Series Studio features an automated machine learning workflow that streamlines the development and deployment of time series-based machine learning models across MCU-class devices, such as the MCX portfolio of MCUs or i.MX RT portfolio of crossover MCUs.

“AI is the key to a world that anticipates and automates based on user wants and needs, but it must be developed in a way that is practical for edge deployment,” said Charles Dachs, senior vice-president and general manager of industrial and IoT at NXP Semiconductors.

“With ready-to-use tools suitable for both small AI models on MCUs like the MCX portfolio, crossover MCUs like the i.MX RT700, as well as larger, generative AI models running on more powerful devices like the i.MX 95 applications processor, NXP is delivering an unparalleled breadth of options for developers across the full spectrum of AI models and AI-enabled edge processors. NXP is making edge AI truly practical for developers across a wide range of markets.”