Support Library
Prediction
After the model training is completed, you will be redirected to the “Prediction” tab.
Prediction Tab
The “Prediction” tab includes:
Info area
Info represents an overview of your trained Solution.
C Library
C Library allows users to download the resulting model and code for inference on the device.
Web prediction for disabled DSP
Web prediction allows users to start predictions on new data with the Neuton web service. Web prediction is available only for solutions with the turned-off DSP option
REST API Access for disabled DSP
REST API Access allows third-party applications access to the model. REST API is available only for solutions with a turned-off DSP option.
Info Area
In the Info area you can see the following information:
Target metric name and its value
Selected task type
Target variable name
Processed dataset
You can see what data the model was trained on, taking into account the additional settings you have chosen, for example, features created from Feature Extraction.
List of Metrics calculated during training including Model Quality Diagram and Model Quality Index. Two types of metrics are displayed: cross-validation and holdout (provided the holdout dataset was used prior to training).
Analytics Tools
Model-to-data relevance indicator (for disabled DSP)
Total footprint
Here you can find information on the estimated usage of SRAM and FLASH memory by the model, calculator, and preprocessing. Estimated values are provided for Cortex M0 и Cortex M4 (these values are provided as an example).
C library

The archive contains the following folders and files:

artifacts – contains models converted to various formats, as well as an executable file for predictions on the desktop.

neuton – contains libraries for embedding, Cortex M0, Cortex M4 and STMicro ISPU are supported.

neuton-generated – contains information necessary for the correct operation of libraries.

LICENSE – contains the possibilities and restrictions on the use of Neuton’s intellectual property.

README – contains instructions for leveraging libraries.

We don't recommend that you modify any files in the archive. Unsupervised changing of files may cause errors in model inference.

After the model training is completed, you will be redirected to the “Prediction” tab.
Prediction Tab
The “Prediction” tab includes:
Info area
Info represents an overview of your trained Solution.
C Library
C Library allows users to download the resulting model and code for inference on the device.
Info Area
In the Info area you can see the following information:
Target metric name and its value
Selected Task type
Target variable name
Training dataset name
List of Metrics calculated during training including Model Quality Diagram and Model Quality Index
Total footprint
Here you can find information on the estimated usage of SRAM and FLASH memory by the model, calculator, and preprocessing. Estimated values are provided for Cortex M0 и Cortex M4 (these values are provided as an example).
C library

The archive contains the following folders and files:

artifacts – contains models converted to various formats, as well as an executable file for predictions on the desktop.

neuton – contains libraries for embedding, Cortex M0, Cortex M4 and STMicro ISPU are supported.

neuton-generated – contains information necessary for the correct operation of libraries.

pipeline – contains artifacts for audio data preprocessing. It is not used in tasks related to sensor data.

LICENSE – contains the possibilities and restrictions on the use of Neuton’s intellectual property.

README – contains instructions for leveraging libraries.

We don't recommend that you modify any files in the archive. Unsupervised changing of files may cause errors in model inference.

After the model training is completed, you will be redirected to the “Prediction” tab.
Prediction Tab
The “Prediction” tab includes:
Info area
Info represents an overview of your trained Solution.
Web prediction
Web prediction allows users to start predictions on new data with the Neuton web service.
REST API Access
REST API Access allows third-party applications access to the model.
Downloadable Solution
Neuton’s downloadable solution allows users to download the resulting model and build it in executable code. For user convenience, the archive contains code in Python. The archive within the downloadable solution can be used independently for predicting on new data without platform assistance.
Info Area
In the Info area you can see the following information:
Target metric name and its value
Selected Task type
Target variable name
Training dataset name
Processed dataset. You can view what data the model was trained on based on additional settings you choose, such as Data Preprocessing.
List of Metrics calculated during training including Model Quality Diagram and Model Quality Index
Analytics Tools
Model-to-data relevance indicator






Stay updated, join the community
slack