Support Library
Data Uploading and Setup
Step 1: Select data for training
The model creation process within Neuton begins with creating a new Solution. The solution is the object for training parameters specification and prediction processes management. Only one model can be built within one solution.
My Solutions. Default View.
After you have worked with Neuton and created some solutions, you can view and manage your solutions in the “My Solutions” workspace:
My Solutions
To create a new solution with a list of previously created solutions click “Add New Solution”. The “New Solution” pop-up window will appear.
Add the desired “Solution Name” in Latin letters.
New Solution
After that, click “Next” to go to dataset import/selection.
Training dataset selection
Please read first about the requirements for training data in the Dataset requirements section.
Uploading Options
To select the dataset you have the following options (tabs):
Uploaded Datasets
This tab allows you to upload your own dataset. (This option is not available for the test-drive version.) Also, you can select one of your previously loaded datasets.
Preloaded Use Cases
Neuton provides preloaded datasets (for demonstration and testing purposes).
Select one of these options to specify the training dataset for your solution. One dataset is used to train one model. If your data is represented by several datasets, you need to combine them in advance.
Upon uploading data to the platform, the data is encrypted in the cloud. All the resulting datasets and models are encrypted as well. Check out the Storage section for more details.
Step 2: Upload dataset

Please select “Click to upload CSV file” and browse to the file location on your hard drive (or drag & drop):
Uploading a Dataset
During the uploading process platform checks the dataset. If you see an error message you should verify the dataset and upload it again. When the file is successfully uploaded you will see a green check mark.
Machine learning operations cannot be performed on inappropriate data structures and variable types. Please make sure your dataset is processed accordingly. To read more about dataset requirements please refer to the “Dataset requirements” section.
When the file is uploaded you can preview the selected dataset in the web interface using the "lens" icon. To go to the next steps, press “OK”.
The file name must not contain the following characters: !/[+!@#$%^&*,. ?":{}\\/|<>()[]] If you upload a file with these characters, the platform will automatically rename the file to remove invalid characters from the name and inform you about it.
When uploading a file, the platform checks the uniqueness of the file name. If a file with the same name has already been uploaded, the platform will offer to rename the newly uploaded file. For optimal storage usage, it is recommended to upload a file to the platform once and then select it from the storage.
Selection of Uploaded Datasets

Select one of the existing datasets by navigating to a dataset that has been previously uploaded:
Selection of Uploaded Datasets
Preloaded Use Cases
Select one of the preloaded datasets by choosing the “Preloaded Use Cases” tab and navigate to the dataset that has been preloaded with Neuton.
To view information about the dataset, click on the corresponding question mark icon “?”
Preloaded Use Cases
On the Dataset, Training, and Prediction tabs for the preloaded datasets, all settings are preconfigured.
Step 3: Specify dataset options
After the training dataset has been defined you should specify the target column. Also, at this stage, you can specify the dataset for holdout validation and drop some feature columns which you consider as irrelevant.
Dataset Options
To enable holdout validation and specify the dataset for it, turn on the switch button near holdout validation. With the holdout dataset specified the training process will happen in the same way as without the holdout dataset but after model training completion, metrics will be calculated on the holdout dataset you uploaded. Otherwise, the platform will measure the validation metric at each training iteration using a 10-fold cross-validation approach. Neuton has a built-in patented feature to prevent overfitting (overtraining) which stops training right before overfitting starts to occur.
The holdout validation dataset must be in the same format as the training dataset.
To exclude some features from the training dataset, mark the check box for the appropriate feature name in the “Remove variables” section. The model will not train on the excluded data. If you select variables to delete, they will be deleted both in the training dataset and in the validation dataset automatically.
If you are making predictions on the platform, it is acceptable to submit data for the test with columns that you have removed in the training and validation datasets. The platform will simply ignore these columns and make predictions without them. For predictions on the device, it is necessary to exclude this data and not feed it on the inference.
Click “Next” to proceed to the training stage.
Step 1: Preparing data for training
On the starting page My Solutions, click the Add New Solution button.
My Solutions. Default View.
In the pop-up window, choose the Input Data Type (Audio Data), specify a Solution Name, and click Next.
New Solution. Pop-up Window.
Step 2: Process data
If you have a ready-made dataset processed with our application, you can select it from storage.
Select Dataset for Training
Otherwise, download our Audio Preprocessing Desktop Application to process audio files in wav or wave formats and upload the dataset generated by our application to the platform.
Currently, the application is available only for Windows.
Neuton audio preprocessing app requires no installation. When downloading is complete, you can run the app to specify the file path and preprocessing parameters.
Audio Preprocessing Desktop Application
The following settings are available in the application:
Audio files folder
This is a path to your raw audio files in wav or wave formats. The folder must contain subfolders with samples of the same class (label). Subfolder name will be used for class labeling.
Output file folder
The folder for the resulting processed CSV file.
Output file name
The file name is generated automatically. It is strongly recommended to leave the file name unchanged as the file name is used for parsing audio processing parameters during model training.
Spectrogram Height (pxls)
Specify desired spectrogram height in pixels.
Spectrogram Width (pxls)
Specify desired spectrogram width in pixels.
Frequency of data (Hz)
Specify sampling rate in Hz.
Audio length (ms)
Specify the duration of audio files in ms.
Window width for FFT
Specify the number of samples for which spectrogram will be built using fast Fourier transform.
All parameters have default values, but you can change them depending on the data and the task being solved.
After defining with settings, click the Start Audio Preprocessing button.
Step 3: Upload the dataset
Your CSV file will be saved to the output file folder.
Drag and drop the generated dataset to the platform.
Since the file is generated by our application, all the data already meets the requirements of the platform. You cannot change the file name and its content in order to avoid incorrect model training or errors in the platform.
Uploaded Dataset
Click on the "lens" icon to see the dataset details.
To calculate metrics on the new portion of data that won’t be used in model training, upload a holdout validation dataset. You have to convert your wav files to the validation dataset with the same settings as in the training dataset using our application.
Holdout Validation
Then click Next and you will be redirected to the Training tab.
Step 1: Select data for training
The model creation process within Neuton begins with creating a new Solution. The solution is the object for training parameters specification and prediction processes management. Only one model can be built within one solution.
My Solutions. Default View.
After you have worked with Neuton and created some solutions, you can view and manage your solutions in the “My Solutions” workspace:
My Solutions
To create a new solution with a list of previously created solutions click “Add New Solution”. The “New Solution” pop-up window will appear. Choose the input data type you will use for your project: audio, sensor, or tabular.
Tabular data must be selected if you solve a task with tabular data which does not belong to a TinyML field.
Select sensor data if you plan to run models on tiny devices and even if:
data was collected not only from sensors
data is already pre-processed
Add the desired “Solution Name” in Latin letters.
New Solution
After that, click “Next” to go to dataset import/selection.
Select Data (Dataset tab)
Please read first about the requirements for training data in the Dataset requirements section.

Training dataset selection
Please read first about the requirements for training data in the “Dataset requirements” section.
Uploading Options
To select the dataset you have the following options (tabs):
Upload dataset
This tab allows you to upload your own dataset. (This option is not available for the test-drive version.)
Select dataset from storage
On this tab you can select one of your previously loaded datasets.
Preloaded dataset
Neuton provides preloaded datasets (for demonstration and testing purposes).
Select one of these options to specify the training dataset for your solution. One dataset is used to train one model. If your data is represented by several datasets, you need to combine them in advance.
Upon uploading data to the platform, the data is encrypted in the cloud. All the resulting datasets and models are encrypted as well. Check out the Storage section for more details.
Step 2: Upload dataset

Please select “Click to upload CSV file” and browse to the file location on your hard drive (or drag & drop):
Select Dataset from Storage
During the uploading process platform checks the dataset. If you see an error message you should verify the dataset and upload it again. When the file is successfully uploaded you will see a green check mark.
Machine learning operations cannot be performed on inappropriate data structures and variable types. Please make sure your dataset is processed accordingly. To read more about dataset requirements please refer to the “Dataset requirements” section.
When the file is uploaded you can preview the selected dataset in the web interface using the "lens" icon. If you have selected the wrong file by mistake you can click on the trash icon to select another dataset. To go to the next steps, press “OK”.
The file name must not contain the following characters: !/[+!@#$%^&*,. ?":{}\\/|<>()[]] If you upload a file with these characters, the platform will automatically rename the file to remove invalid characters from the name and inform you about it.
When uploading a file, the platform checks the uniqueness of the file name. If a file with the same name has already been uploaded, the platform will offer to rename the newly uploaded file. For optimal storage usage, it is recommended to upload a file to the platform once and then select it from the storage.
Select dataset from storage

Select one of the existing datasets by choosing the “Select dataset from storage” tab and navigate to a dataset that has been previously uploaded:
Select Dataset from Storage
Preloaded Dataset
Select one of the preloaded datasets by choosing the “Preloaded dataset” option and navigate to the dataset that has been preloaded with Neuton.
To view information about the dataset, click on the corresponding question mark icon “?”
Preloaded Dataset
On the Dataset, Training, and Prediction tabs for the preloaded datasets, all settings are preconfigured.
Step 3: Specify dataset options
After the training dataset has been defined you should specify the target column. Also, at this stage, you can specify the dataset for holdout validation and drop some feature columns which you consider as irrelevant.
Dataset Options
To enable holdout validation and specify the dataset for it, turn on the switch button near holdout validation. With the holdout dataset specified the training process will happen in the same way as without the holdout dataset but after model training completion, metrics will be calculated on the holdout dataset you uploaded. Otherwise, the platform will measure the validation metric at each training iteration using a 10-fold cross-validation approach. Neuton has a built-in patented feature to prevent overfitting (overtraining) which stops training right before overfitting starts to occur.
The holdout validation dataset must be in the same format as the training dataset.
To exclude some features from the training dataset, mark the check box for the appropriate feature name in the “Remove variables” section. The model will not train on the excluded data. If you select variables to delete, they will be deleted both in the training dataset and in the validation dataset automatically.
If you are making predictions on the platform, it is acceptable to submit data for the test with columns that you have removed in the training and validation datasets. The platform will simply ignore these columns and make predictions without them. For predictions on the device, it is necessary to exclude this data and not feed it on the inference.
Click “Next” to proceed to the training stage.





Stay updated, join the community
slack