Sign in Start for free


Make your Edge Device intelligent
No Model Size & Quality Trade Off
Our unique framework empowers users to always create neural networks of optimal size and accuracy
Up to 1000 times
Fewer coefficients and neurons
Smaller in size (Kb)
Faster inference
* in comparison to TensorFlow
Neuton's models are so compact that they can run on any microcontroller
No compression techniques (quantization, pruning, etc.)
Accuracy is not affected
Neuton is a No-Code Automated TinyML Platform
Check out a 2-minute video about how it works
Builds tiny and explainable models with three clicks, without need for coding nor Machine Learning experience.
Supports 8, 16, and 32 bit microcontrollers
Solves tasks for regression, time series, classification, anomaly detection with sensor, audio and tabular data. Support for image and video is on the roadmap.
Learn How Neuton Creates Incredibly Compact and Accurate Models
Neuton allows building predictive models optimized in size and accuracy automatically in a single iteration. Read more about our unique neural network framework for creating compact models.
5 Unique Features of Neuton Network Framework
Selective connections
Unique algorithm
Automatic structure growth
No manual search
Constant cross-validation
Selective tinymodels to connected features
First, Neuton uses a selective tinymodels to connected features. Neuton only needs to make connections with the most important features
Unique patented global optimization algorithm
We leverage a unique patented algorithm to adjust the coefficients within a model. Unlike most algorithms Neuton's algorithm is not based on backward propagation of errors and the stochastic gradient descent. Furthermore, the Neuton algorithm minimizes the likelihood of hitting local minima. This is especially important when building small models where the probability of hitting local minima is particularly high. Our algorithmic tinymodels helps to avoid this issue.
Automatic neuron-by-neuron network structure growth
The Neuton platform enables models to be built automatically, neuron by neuron, starting from learning general features and moving toward identifying the most specific ones. This allows selection of a model of almost any level of precision and size, in a single iteration.
No manual search for neural network parameters
Neuton eliminates the time-consuming multidimensional manual search for neural network parameters (number of layers, neurons in a layer, type of activation function, batch size, learning rate, etc.) and allows one to quickly & efficiently find the optimal structure.
Constant cross-validation
The step-by-step growth of the neural network makes it possible to cross-validate with the addition of each neuron, which is typically not feasible with a standard tinymodels. Furthermore, constant cross-validation increases the generalizing capabilities of the model, which allows for creation of compact models - without compromising accuracy.
Create Tiny Models without Сompression
Neuton models maintain all of their original characteristics, without any reduction of accuracy. Neuton does not reduce the model size after its creation.
Neuton does not use quantization, pruning, clustering, nor distillation.
Evaluate the Uniqueness of our Approach
by Comparing our Benchmarks
For example, Neuton's Model for Combined Cycle Power Plant Data Set is 208.6 times smaller than TensorFlow, and 42.3 times smaller than TensorFlow Lite.
Size, kB
Target metric
Holdout metric
2 338
TensorFlow Lite
Combined Cycle Power Plant Data Set 
The dataset contains 9,568 points collected from a Combined Cycle Power Plant over 6 years. Features consist of hourly average ambient variables (Temperature, Ambient Pressure, Relative Humidity and Exhaust Vacuum) used to predict the net hourly electrical energy output.
Embed into Edge Devices
Neuton's models can be built into microcontrollers and into other small compute devices, with limits as challenging as the following characteristics:
Energy - 10s-100s mAh
Processor < 100 MHz
Memory < 100 Kb
Explore the Case Studies
Smart Cities
Transportation & Logistics
Edge devices for home monitoring
Edge devices allow monitoring home appliances in real-time on the device, without sending data to the cloud with more privacy and security.
Home Security and Automation
With Neuton, it is easy to build compact ML models that will allow you to create Home security and automation systems using edge devices.
People and Pet Tracking
Neuton TinyML models are a perfect foundation for building People and Pet Tracking systems, allowing you to detect the location of your child or pet.
Asset Tracking
Neuton allows building models that can be embedded into edge devices with location-based analysis tools to perform AI-driven asset tracking
Commercial Building Automation
Tiny ML allows the creation of cutting-edge Commercial Building Automation systems. Manage energy consumption, heating, ventilation, and electricity by analyzing hundreds of variables straight from the devices.
Condition-based monitoring
Neuton TinyML models are used for real-time condition-based monitoring. Embedded edge devices provide 100% uptime and do not require an internet connection. (128)
Smart Cities
Neuton TinyML models play an important role in the development of next-generation city management systems. It's safer to regulate traffic, heat supply, lighting, and much more directly on the devices.
Smart Parking
AI-driven Smart Parking is performed at the device with the minimum energy consumption and doesn't require an internet connection, ensuring that your data remains private.
Smart Lighting
Cities can boost operational efficiency, and save costs by using AI-driven lighting to optimize dimming, or on/off schedule. All these operations can be performed right on the device.
Fleet management systems
Neuton TinyML models allow you to create Fleet Management systems right on the devices, which makes these systems more independent, sustainable and allows you to carry out logistics operations right on the device.
Heavy Transport Vehicles and Equipment
TinyML models can be embedded into compact devices, allowing you to do AI-driven calculations right on the device. Monitor the status of Vehicles and Equipment without transferring information to the cloud and consuming a minimum of energy.
Smart Cars
Neuton TinyML models allow you to create smart car control systems that do not depend on the transfer of information to the Internet. Calculate the temperature of hard-to-reach parts, predict breakdowns, diagnose problems - all this can be done right on the device.
Smart grid
Smart grid system implemented directly on the devices allows you to quickly detect irregularities in the quality of the power supply and other problems, even without constantly sending data to the Internet.
Smart meters
Neuton models are so compact that they allow creating utilities control systems directly on devices. Control gas, electricity, and other utilities without sending information to the cloud.
Air Quality
Neuton TinyML models can be easily embeded into edge devices, allowing you to do smart data analysis straight from ambience monitoring sensors.
Water Quality
TinyML models can be easily embedded into the smallest devices that allow you to control Water Quality by analyzing dozens of factors right on the device.
Radiation level
Neuton allows building compact models on the smallest devices that allow you to control Radiation levels by analyzing dozens of factors right on the device.
Neuton Pricing and Options
Zero Gravity
Self-service free unlimited plan.
Enterprise Plan
Get assisted and supported
Use our service absolutely free of charge, covering only your Google Cloud Platform infrastructure costs. Get up to $500 in credits for infrastructure
Unlimited number of models
Data Preprocessing
Feature Engineering
Unlimited number of predictions via the web interface, REST API or downloaded models
Exploratory Data Analysis
Model Interpreter
Model Quality Diagram
Model Decay Indicator
Only pay for what you use. Google Cloud Platform Costs
Minimum 100 hours of training included
We provide a full range of data science services, from identifying the task objectives to its deployment into production. Our experts will pass the knowledge to your team enabling you to implement dozens AI solutions independently on a daily basis.
Support 24/7
Free onboarding
Dedicated team: Data Scientist, Embedded Engineer, Project Manager
Comprehensive approach
Revealing the potential of AI
Identifying the most important AI cases
Identifying the necessary data for the use case
Data preparation, feature engineering
Building an optimal model, evaluating its quality and size
Identifying the most important factors and data-driven insights
Embedding a model into the device
Evaluating business results
We will train your team to
Make AI-driven decisions within days using no-code Auto ML platform
Identify the necessary data for building a model
Build compact models automatically and evaluate their quality and size
Find data insights and identify hidden patterns
Embed models into the tiniest Edge devices
Manage the lifecycle of a model and update it
Tabular Data VS Computer Vision: Detecting Room Occupancy

Learn why room occupancy detection using environmental sensors and tabular data wins over computer vision.

What if we say that there’s a more budget-friendly way to detect occupancy than real-time video analysis?

Read more
Tiny ML case: Smart Shipment with Arduino IDE

Worrying about whether your parcels are transported safely? Check out the new project to learn how you can apply TinyML to easily track the status of your packages and monitor if they are moving, staying in the same place, impacted, thrown, picked up, placed in the wrong position, etc.

Read more
TinyML: Slope control for robots with Arduino Pro

Do you often find your "smart" vacuum cleaner stuck or blocked by a carpet, a doorstep, or even your brand new shoes? It’s quite an annoying situation, isn’t it? Learn how to make your robot smarter in a few steps by running a TinyML model on an Arduino Pro board, Nicla Sense ME.

Read more
Unlock Passwords with TinyML-based Digit Recognition

We are happy to introduce the new case of our ambassador, Sumit Kumar «Unlock Passwords with TinyML-based Digit Recognition».
Perform the MNIST digit recognition on passwords using the TinyML approach on a tiny MCU.

Read more
Neuton's Divine Journey
To make the world a better place by augmenting human ingenuity through wider adoption and usage of artificial intelligence, while having a transformative impact on the economy, all industries, their associated scientific breakthroughs and overall quality of life.
Infrastructure Credits
Use Neuton's free Zero Gravity plan, accompanied by eligible free trial credits to cover infrastructure costs.
Register as a new customer within the Google Cloud Platform to be eligible for up to $300 in free trial credits.
Corporate customers are also eligible for an additional $200 in credits on top of the $300 free trial credits. In order to be qualified to redeem the additional $200 credits, customers must register as a new customer with Neuton using a corporate email domain (no personal email accounts allowed, e.g. Gmail, Yahoo).
Once the customer has exceeded the available credits, infrastructure fees will then be changed until the subscription is terminated. The subscription may be canceled at any time by cancelling the pricing plan.
Google Cloud Platform Costs:
To build models with your data, an IT infrastructure is required. Google Cloud Platform (GCP) uses virtual machines. Every model can be trained in parallel without losing speed. That is why each dataset training requires a separate virtual machine with enough GPU. The platform automatically chooses and provisions the right infrastructure for your dataset to ensure fast learning.
The costs are calculated as follows:
Storage - $0.04 GB/month
Prediction - $0.04 per hour per model. The cost applies only during the time when the prediction button is enabled.
Training - The cost per model for the training of one dataset depends on the number of rows in it and varies from $0.88-4.82
Training Costs per dataset size, per hour of training, per model
0-1000 rows of data - $0.88
1001-5000 rows of data - $1.44
5001-50,000 rows of data - $2.56
>50,000 rows of data - $4.82
For new accounts, GCP provides up to $500 credits, for the next 90 days. $500 is enough for at least 100 hours of training on the platform!
Contact Us
Get in touch to learn more
Contact Us
Contact Us
Thank you!
Please check your inbox. We will reach out to you shortly with the next steps.