Learn Neural Designer
Follow practical tutorials, explore real examples, and learn how to build, validate, and deploy machine learning models with Neural Designer.
Choose your learning path
Start with the product workflow, go deeper into machine learning concepts, or jump straight to applied examples and use cases.
Build a model step by step
These core tutorials follow the same sequence you use in Neural Designer: prepare data, design and train the model, validate it, and deploy the result.
Data set
Prepare variables, samples, missing values, and data partitions.
Model types
Choose between approximation, classification, forecasting, text, image, and anomaly detection models.
Neural network
Review inputs, layers, outputs, and model structure.
Training strategy
Configure losses, optimization, and regularization.
Model selection
Select the architecture that generalizes best.
Testing analysis
Evaluate accuracy, errors, residuals, and classification metrics.
Model deployment
Export predictive models and integrate them into your workflow.
7-step guide
Put the full process together in a practical Neural Designer guide.
Examples by application area
Examples now follow the same four-area classification used across the site, with engineering first because it contains the broadest set of applications.

Engineering and Technology
Mechanical, electrical, civil, chemical, manufacturing, energy, automotive, aerospace, and marine applications.
View examples
Science
Physics, chemistry, biology, environmental science, materials, biotechnology, agriculture, and food science.
View examples
Medicine and Health Sciences
Medicine, public health, pharmacology, drug discovery, and biomedical engineering applications.
View examples
Business and Economic Sciences
Finance, insurance, marketing, sales, management, operations, human resources, and economics.
View examplesBrowse all resources
Filter the learning library by resource type or search for a specific topic.
Introduction to neural networks
Start with the main machine learning concepts used by Neural Designer.
Types of machine learning models
Compare approximation, classification, forecasting, text, image, and anomaly detection models.
Testing analysis
Evaluate model performance with error, regression, and classification analyses.
Integrate a model in Power BI
Bring Neural Designer model outputs into reporting workflows.
Engineering examples
Applications in industrial systems, energy, automotive, aerospace, and more.
Science examples
Applications in physics, chemistry, biology, environment, materials, and food science.
Medicine examples
Applications in medicine, public health, pharmacology, and biomedical engineering.
Business examples
Applications in finance, insurance, marketing, sales, operations, and economics.
Advanced analytics
Understand how predictive models support data-driven decision-making.
Modeling process
Review the steps involved in building reliable machine learning models.
Data sets and data matrices
Learn the tabular structures behind supervised learning problems.
Genetic algorithm feature selection
Use optimization techniques to identify relevant inputs.
No resources match that search.
Ready to build a model?
Start with the guided workflow or download Neural Designer when you are ready to apply these resources to your own data.
Download Neural Designer