Neuton
Automated Machine Learning
Create Machine Learning solutions in just a few clicks, without coding or ML experience
Neuton's Business Outcomes
Solve regression, time series, binomial and multinomial classification problems to:
Explore business insights
Do predictive analytics
Make smart forecasts
Reveal correlations
Perform rankings
Perform segmentation
Ease of Use
Straightforward interface with a fully automated process
Beautiful and user-friendly interface and layout
AI solution creation in 3 clicks
No coding or experience in data science needed
Ease of Use
Upload your data easily via drag & drop
Work with text, categorical variables, floats, integers, and time series
Train your Models
Fast and fully automated process
Use your models for prediction
via Web interface, REST API or on your on-premise software
State of the Art Data Preprocessing and Feature Engineering
Missing values imputation using tree based machine learning models
Analysis of feature correlations with the target variable
Creation of feature interactions
Unique Resulting Models
Self-growing and learning
Up to 100 times smaller and faster than those built with other solutions
Accuracy is not affected by compactness
Neuton Explainability Office ®
Exploratory Data Analysis
Feature Importance Matrix with class granularity
Model Interpreter
Feature Influence Indicator
Validate Model on New Data
Model-to-Data Relevance Indicators historical and for every prediction
Model Quality Index
Confidence Interval
Extensive list of supported metrics with Radar Diagram
Neuton Pricing and Options
Training
GPU Training and Model Creation
Unlimited
Prediction
Web interface
100 Rows per Prediction File
REST API
5000 API Requests Per Month
On-premise
No Downloadable Models
Infrastructure
Google Cloud Platform Costs:
Cloud Storage, per GB per month* – $0.04
GPU Training, per hour - $0.70
Prediction, Hosted Model, per hour - $0.04
Estimated Monthly Costs based on 1 hour of training and 1 month of prediction:
$46.00 reimburse all costs with your employer or
Get up to $500 in credits
$0/mo
Training
GPU Training and Model Creation
Unlimited
Prediction
Web interface
Unlimited
REST API
Unlimited
On-premise
No Downloadable Models
Infrastructure
Google Cloud Platform Costs:
Cloud Storage, per GB per month* – $0.04
GPU Training, per hour - $0.70
Prediction, Hosted Model, per hour - $0.04
Estimated Monthly Costs based on 1 hour of training and 1 month of prediction:
$46.00 reimburse all costs with your employer or
Get up to $500 in credits
$1,999/mo
$2,699/mo
Training
GPU Training and Model Creation
Unlimited
Prediction
Web interface
Unlimited
REST API
Unlimited
On-premise
No Downloadable Models
Infrastructure
Google Cloud Platform Costs:
Cloud Storage, per GB per month* – $0.04
GPU Training, per hour - $0.70
Prediction, Hosted Model, per hour - $0.04
Estimated Monthly Costs based on 1 hour of training and 1 month of prediction:
$46.00 reimburse all costs with your employer or
Get up to $500 in credits
$1,999/mo
$2,699/mo
Billed monthly
Training
GPU Training and Model Creation
Unlimited
Prediction
Web interface
Unlimited
REST API
Unlimited
On-premise
Downloadable Models
Infrastructure
Google Cloud Platform Costs:
Cloud Storage, per GB per month* – $0.04
GPU Training, per hour - $0.70
Prediction, Hosted Model, per hour - $0.04
Estimated Monthly Costs based on 1 hour of training and 1 month of prediction:
$46.00 reimburse all costs with your employer or
Get up to $500 in credits
$3,999/mo
Billed monthly. One year commitment.
Video Tutorial
Watch a video tutorial how to use Neuton in detail
Features
Support
All Things Neuton
Free Credits
You can use Neuton’s Gravity free 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 you have exceeded your available credits, you will then be charged infrastructure fees until you stop usage or terminate the subscription. You may cancel the subscription at any time by cancelling your plan.
Info
* Includes Network Egress, Backup, Monitoring
** Estimated monthly infrastructure costs are based on 24 hours of GPU usage for training, 30 Days of hosting for one model for predictions, uploaded data size (training datasets) ~1 GB. Pricing for Neuton’s First Law, Second Law and Neuton’s Third law excludes infrastructure costs.
Explore business insights
Look for the most crucial factors affecting our business:
Why users subscribe, start using credit cards, want to switch to a competitor, or why employees leave your company.
Why sales drop, demand for on some goods increase, ticket size decreases, or why revenue structure changes
Find answers with Neuton.
Do predictive analysis
Predict risks: loan default probability or car accident
Take preventive measures: identify customers who wants to stop using the product or go to a competitor, employees that are at risk to churn
Set up an automated calculator for real estate price forecasts or insurance risk assessments
Make smart forecasts
Neuton allows you to analyze many factors in forecasting and, as a result, to get as close as possible to meeting goals and realizing business expectations:
Make plans according to daily dynamics or seasonal fluctuations
Identify key factors affecting the forecast
Determine what kind of plans to allocate to specific employees, units, departments, etc.
Reveal correlations
Identify hidden links and correlations and open up new opportunities for business optimization:
Is there a connection between the success of a particular call center operator and the type of client called?
Is there a connection between employee IQs and the success of their projects?
Is customer income related to a customer’s willingness to make another purchase?
Perform rankings
Focus on the most crucial factors to help you achieve the best results. Neuton allows you to rank lists based on the probability of success:
Sell to prospects that are more likely to complete a deal
Call customers who are more likely to buy something
Start collecting debt from people who are more likely to be able to pay
Perform segmentation
Segment based on multiple factors. Find your target profiles and effectively focus your efforts
Identify the perfect employee or user profiles
Create custom segmentation for your own unique business needs
Self Signup
Easy and intuitive registration and subscription process
No need to schedule an appointment with a sales representative to get access to the service
Single Web Interface
Single web interface for both training and prediction
Full model creation process is performed in a single window - from data upload to predictions. Wizard walks you through the steps for creating a model->Upload->Train->Predict
Web interface for predictions: batches (upload/download csv files)
No need to juggle multiple portals or menus for full control including working with VM
Simple and straightforward interface
Easy model creation in “3 clicks”
Intuitive and user friendly workflow with minimum technical terms
No coding required for infrastructure provisioning and setup
Single dashboard displays all AI models, their statuses, target metrics and VM statuses
Training can be stopped and resumed in one click from the same point, thus saving time and infrastructure costs
Clear web prediction interface, no need to transform a dataset to the specific JSON format (data is uploaded in a raw csv file)
Prediction results can be viewed within the web interface or downloaded
Fully automated process
Automated infrastructure provisioning and deprovisioning includes:
Creation of buckets for datasets
Enablement of Virtual Machines for training
VM deprovisioning when an experiment is complete
Provisioning of an allocated VM for every experiment run, thus avoiding resource consumption conflicts between different experiments
Automated selection of settings (task type, target metric, preprocessing and time limitations)
Advanced preprocessing and feature engineering. Neuton even fills in missing values using intelligent algorithms, can combine up to 4 original features during feature engineering, and uses supporting models to process raw datasets.
Enabling Predictions (model deployment in the cloud) with a single click of a mouse
Neuton REST API can be used to augment your device or service with AI capabilities. We offer examples of how to use it with several different programming languages.
Upload your Dataset
Just upload your dataset in a CSV format and tart training. Neuton works with text, categorical variables, floats, integers, and time series.
Neuton has smart algorithms for task-type detection based on target variable values, and perfectly detects regression from multi classification tasks even when there are more than 100 classes.
Neuton can solve time series problems and supports relative time intervals. There is no need to specify group by field if you don’t have unique values in time and date columns, as the Neuton preprocessing pipeline can work in automatic mode.
Neuton also supports working with text fields, automatically detecting text features in the dataset and using them to create new features to use during model training.
Fully automated process
Automated infrastructure provisioning and deprovisioning includes:
Creation of buckets for datasets
Enablement of Virtual Machines (VM) for training
VM deprovisioning when an experiment is complete
Provisioning of an allocated VM for every experiment run, thus avoiding resource consumption conflicts between different experiments
Automated selection of settings (task type, target metric, preprocessing and time limitations)
Advanced preprocessing and feature engineering. Neuton even fills in missing values using intelligent algorithms, can combine up to 4 original features during feature engineering, and uses supporting models to process raw datasets.
Enabling Predictions (model deployment in the cloud) with a single click of a mouse
Fast training
Faster Training (in comparison to those of AI/AutoML Giants and most Venture Backed AI/AutoML Companies)
Progress bar makes it clear when the training process is about to complete
You can both stop and resume training in one easy click
Web prediction
Web prediction allows users to start predictions on new data with the Neuton web service. Just upload a dataset with new data and get the predictions in web interface.
REST API Access
Neuton REST API can be used to augment your device or service with AI capabilities. We offer examples of how to use it with several different programming languages.
Downloadable solution
You can download a Neuton model and use it online or offline without subscription. The archive contains the model in binary format and other supporting scripts and objects that, along with a simple python script, pulls it all together when predicting on new data. The downloadable model is absolutely free to use after the initial download, and requires no further access to the Neuton Platform nor license key.
State of the Art Data Preprocessing and Feature Engineering
Data Preprocessing
Data preprocessing is one of the most important steps in automated machine learning, as the quality of a training dataset greatly affects the prediction outcomes. Neuton performs this time-consuming process automatically, so you don’t need to worry about missing values or irrelevant data.
The automated data preprocessing stage includes:
Rules induction from data
Dataset cleaning
Missing value imputation using the tree based machine learning models
Removal of duplicates and outliers
Variables transformation
Data sampling
Binomial and multinomial data correlation tests
Data scaling and normalization
Text field detection, creation of bag-of-words, TF/IDF, etc.
Feature Engineering
Feature engineering allows you to extract new input features from your data to improve the performance of machine learning models.
The automated feature engineering stage includes:
Baseline model scoring
Feature selection
Creation of feature interactions based on linear models and on tree-based models
Search, examination and removal of mutually correlated features
Feature importance ranking
Unique Neural Framework
Neuton AutoML is based on a proprietary neural network framework developed by our team of scientists. Neuton’s resulting models are incredibly compact and fast.
Unique characteristics of the resulting model:
Self-growing structure, has 5 fold cross-validation with minimum overfitting
Up to 100 times smaller (neurons, coefficients, Kb size) models
Up to 100 times faster prediction
Can be built into microcontrollers and other small compute devices
Model accuracy is higher than those of AI/AutoML Giants and most Venture Backed AI/AutoML Companies
Neuton works perfectly with datasets of any size, and unlike Google or Amazon you can train a model on data with fewer than 900 rows just as effectively as with datasets that are many Gigabytes in size.
Most of Neuton’s competitors build multiple models in an effort to determine the best option. Neuton effectively and efficiently solves most problems simply by utilizing our single neural framework. The result is an overall reduction in infrastructure costs, a savings passed along to the user.
Unique Neural Network training algorithm guaranteeing the best model predictive power
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.
Register for our next Webinar