There is a newer version of the record available.

Published May 21, 2026 | Version v0.6.3

Zero2Neuro: a No-Code Toolbox for Constructing, Training, and Evaluating Deep Neural Network Models

Description

Zero2Neuro is a no-code toolbox for constructing, training and evaluating Deep Neural Network (DNN) models for a wide range of modeling problems. This package provides easy-to-use solutions for:

  1. Loading data stored in a variety of formats (including the common Comma Separated Values format), and configuring the data for use in DNN training and evaluation.

  2. Creation of Deep Neural Network models from several flexible DNN model schemata, including fully-connected networks (FCNs), convolutional neural networks (CNNs), and U-Nets. The user specifies the structural details of their specific model.

  3. A standard DNN training and evaluation engine. This engine supports the production of result reports in various formats, including hooks for Weights and Biases.

 

Files

Symbiotic-Computing-Laboratory/zero2neuro-v0.6.3.zip

Files (11.8 MB)

Additional details

Funding

U.S. National Science Foundation
AI Institute: Artificial Intelligence for Environmental Sciences (AI2ES) 2019758
U.S. National Science Foundation
OneOklahoma Cyberinfrastructure Initiative Artificial Intelligence Consultants (ONEOCII-AIC): Developing a pipeline of AI consultants and workforce training program. 2538234

Dates

Available
2026-05-21
First official release

Software