Nordic Edge AI 

Ultra-low-power edge AI across the industry's broadest range of applications 

Your data. Your model. Your edge.

From saving bandwidth and energy to more responsive real-time performance, implementing AI in your embedded applications offers massive benefits beyond the buzzwords. Nordic Semiconductor offers two unique technologies, Neuton models and Axon NPU, exclusively to our customers, to cover the industry's broadest range of devices, applications, and customer needs.

Custom Neuton models

A smarter approach to building edge AI models


 Neuton_Logo_horizontal_Gradient_RGB.png 

Challenge

Traditional neural networks face a fundamental challenge: they require manual architecture design and rely on methods that often produce bloated models with millions of parameters. Data scientists must painstakingly tune dozens of variables, from learning rates to layer depths, in a trial-and-error process that's both resource-intensive and imprecise.

The Neuton models solution

Custom Neuton models takes a radically different approach. Instead of starting with a predetermined structure, it grows neural networks neuron-by-neuron, automatically determining the optimal architecture as it learns. This granular construction process, combined with a patented global optimization algorithm that avoids the pitfalls of traditional gradient descent methods, produces remarkably compact models without sacrificing accuracy.

Result

A fully automated system that requires minimal expertise to use. Simply provide your data and target variable, Neuton handles structure creation, cross-validation, and overfitting control automatically. The framework delivers models that are dramatically smaller than conventional neural networks, enabling faster predictions and deployment on resource-constrained devices, all while maintaining excellent accuracy and generalization capabilities.

Benchmarks

Bearing fault detection case-study

Models built on dataset from Case School of Engineering

 Total Footprint (KB) LiteRT Neuton Neuton Advantages 
NVM
 TinyML framework (model + inference engine + DSP) 
 61.7 6.6

9 times smaller model 
RAM TinyML framework (model + inference engine + DSP) 11.2 1.2

9 times smaller model 
Inference time (ms) 360 1,46

246 times faster 
Holdout validation accuracy 0.79 0.98  19% higher accuracy

Test performed with both Neuton and LiteRT models running on an nRF52840 and tested on the same validation dataset.

"Magic Wand" gesture recognition

 Total Footprint (KB) LiteRT Neuton Neuton Advantages 
NVM
 TinyML framework (model + inference engine + DSP) 
 79.96 5.42

14 times smaller model

43% reduction of total NVM use 
Device drivers and business logic 93.47 93.47
RAM TinyML framework (model + inference engine + DSP) 18.2 1.72

10 times smaller model

26% reduction of total RAM use 
Device drivers and business logic 45.69 45.69
Inference time (µs) 55,262 1,640

33 times faster 
Holdout validation accuracy 0.93 0.94  0.7% higher accuracy

Test performed with both Neuton and LiteRT models running on an nRF52840 and tested on the same holdout dataset.

    Use cases

  • Predictive maintenance and building automation systems

    In building automation systems, embedded machine learning can be leveraged to monitor equipment health in real-time and anticipate failures before they occur. By analyzing sensor data directly on edge devices, these systems can detect patterns and anomalies in HVAC, lighting, and security operations without relying on constant cloud connectivity. This approach reduces downtime, optimizes energy use, and lowers maintenance costs, all while enabling smarter, more responsive building environments.

  • Smart sensor networks with local data analysis on each node

    Smart sensor networks can utilize embedded machine learning to process information directly at the source, reducing latency and bandwidth requirements. Each node can independently detect patterns, filter noise, and make real-time decisions, enabling more efficient and scalable systems. This decentralized approach enhances responsiveness and reliability, especially in applications like environmental monitoring, industrial automation, and smart buildings, where immediate insights and minimal data transmission are critical.

  • Movement and gesture recognition for remote controls and wearable devices

    For remote controls and wearable devices, embedded machine learning enables real-time interpretation of motion data directly on the device. By running lightweight ML models on embedded processors, these devices can accurately detect and classify user gestures without needing constant cloud access. This allows for intuitive, low-latency interactions in applications like touchless control, fitness tracking, and assistive technologies, while maintaining energy efficiency and data privacy.

  • Health and activity monitoring for smart health wearables

    Smart health wearables are increasingly powered by embedded machine learning, enabling real-time analysis of biometric and motion data directly on the device. These wearables can track vital signs, detect irregularities, and classify physical activities with minimal latency. By processing data locally, they improve user privacy, extend battery life, and provide immediate feedback, making them ideal for continuous, personalized health monitoring and early detection of potential medical issues.

Demo videos