Know How To Build A Neural Network with Neuton Framework

There is No Model Size & Quality Trade Off

Neuton’s models are so compact that they can run on any microcontroller

Our unique framework allows creation of a neural network structure of the optimal size & accuracy

Neuton’s models are extremely compact:

Up to 1000 times

Fewer coefficients and neurons

Smaller in size (Kb)

Faster inference

in comparison to Tensor Flow

Bring Intelligence to the Edge!

A comprehensive approach to building exceptionally tiny and explainable models for Data Scientists and non-Data Scientists alike - opens up amazing possibilities for smart devices to do complex computing on the edge. We are solving tasks for regression, time series, classification with tabular data. Support for audio, image and video is on the roadmap.

Automation

Neuton is a zero-code SaaS based AutoML platform developed for All

Unique Neural
Network Framework

Neuton’s disruptive neural network framework builds extremely compact models

Explainability

Neuton Explainability Office offers a unique set of tools for model quality evaluation and understanding the logic behind the model

Learn How Neuton Creates Incredibly Compact and Accurate Models

Selective connections

Unique algorithm

Automatic structure growth

No manual search

Constant cross-validation

Selective approach to connected features

First, Neuton uses a selective approach 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 approach 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 approach. Furthermore, constant cross-validation increases the generalizing capabilities of the model, which allows for creation of compact models - without compromising accuracy.

Build an Efficient Self-Organizing Neural Network

Neuton’s neural network learning is not based on backward propagation of errors and the stochastic gradient descent algorithm, but rather uses a new efficient global optimization algorithm with an excellent generalization capability, allowing for development of the optimal network structure for one iteration.

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.

Algorithm

Size, kB

Coefficients

Target metric

Holdout metric

TensorFlow

31.08

2 338

MAE

3.35

TensorFlow Lite

6.31

n/a

MAE

3.36

Neuton

0.149

100

MAE

3.30

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.

Explore our Benchmarks

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.

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 Study Determining Cardiac Arrhythmias

Learn how to determine cardiac arrhythmias on a microcontroller without the cloud fast and easily leveraging the Neuton AutoML platform.

Explore Use Cases

Improve Quality of your Models Ensembling them with Neuton Models

Thanks to unique model creation approach, models generated by the Neuton Neuron Network Framework enhance any model in the ensemble

Benchmarks

TinyML cases

Well-known Kaggle cases

Number of Coefficients

Size

Score

Task Type:

Learn more

* Similar results are produced with other popular Neural Network Frameworks.

** TensorFlow lite

*** AutoKeras is a Neural Architecture Search (NAS) tool.

Credit Unions Media

01.10.2022

Roadmap for Changing AI from a Banking Catch Phrase to Real Action | The Financial Brand

With the fast-paced AI adoption underway, credit unions have difficulty developing their data strategy and putting it into action due to improper data management.

Partners

12.28.2021

Neuton and SiliconValley4u Shaping Up New Career Opportunities in AI for Students

Our first common course in collaboration with SiliconValey4u for IIM Ranchi students.

Media Partners

12.22.2021

Neuton.AI joins Arm AI Partner Program to Accelerate Deployment of Machine Learning at the Edge

Neuton.AI has joined the Arm® AI Partner Program, to bring intelligence to the edge.

TinyML Media

12.17.2021

AI/ML and Analytics for IoT – 2021

Artificial Intelligence and Machine Learning for the Internet of Things (IoT) in 2021.

Credit Unions Media

12.17.2021

Artificial Intelligence as a Playing Field for Credit Unions | CUInsight

Over the course of the global pandemic, credit unions had to adapt to the changing needs of their members. This process involved embracing a data-driven approach to customer services by using cutting-edge tools such as artificial intelligence and machine learning.

Features

Neuton is Currently Featuring

Neuton’s key capabilities

Problems Neuton is Currently Solving

Regression, time series, classification

Positioned for the Future

Support of Image/Audio/Video, multi host training

Contact Us

Get in touch to learn more

This website uses cookies to give you the best online experience

Accept