Tabular Regressor

Upload a table of training samples

Output sample importances (optional)

Predict the values of:

columns rows

Architecture options

Max weights:
Max neurons:
Max layers:
Max layer skip:

Sparse weights
Include bias
Allow I→O
connections

Instructions: This tool builds neural networks that predict outputs from inputs.

Upload a table^* of training samples containing both inputs and outputs. These examples will train the network. Specify the output rows or columns and click Submit.
The trained network opens in a new page, where you can a) predict the outputs of new samples, and b) export it as computer code for use in your own programs (no attribution needed).

Try it using example data

* Sample table must be a fully numeric, comma-separated .csv file with no empty fields. Max allowed: 100 kB file size, 1000 rows/columns, 1 header row/column. Generation time limited to 1 sec.