Neuton TinyML is an automated no-code platform that empowers users to build extremely compact models and embed them into unbelievably tiny devices, even with 8-bit capacity. The platform has a patented neural network framework under the hood, which was created by our data scientists and is not based on any existing frameworks or non-neural algorithms.
Neuton doesn't create models with a predefined structure. It grows the network neuron by neuron, using a unique patented algorithm to adjust coefficients within a model. It allows users to effectively builds ultra-tiny and accurate models without compression techniques. As a result, the models turn out to be:
with fewer coefficients and neurons
up to 1,000 times smaller compared to other frameworks
Neuton's models can be deployed and run on the smallest MCUs and demonstrate fast inference time.
The Neuton platform is so easy to use that no special data science background is needed. It automates the whole process of creating models for edge devices through the use of innovative and cutting-edge technology. As such, users of all demographics to implement dozens of turnkey AI solutions based on motion, gestures, wake words, and sound recognition.
Neuton is absolutely free for developers worldwide. We also offer an Enterprise plan which perfectly suits for launching large-scale IoT projects as it combines an individual approach and a full cycle of end-to-end data science services.