MATLAB for Machine Learning

Train models, tune parameters, and deploy to production or the edge

Using MATLAB®, engineers and other domain experts have deployed thousands of machine learning applications. MATLAB makes the hard parts of machine learning easy with:

  • Point-and-click apps for training and comparing models

  • Advanced signal processing and feature extraction techniques

  • Automatic hyperparameter tuning and feature selection to optimize model performance

  • The ability to use the same code to scale processing to big data and clusters 

  • Automated generation of C/C++ code for embedded and high-performance applications

  • Popular classification, regression, and clustering algorithms for supervised and unsupervised learning

  • Faster execution than open source on most statistical and machine learning computations

Main Features of Machine Learning

Interactive Apps and Algotithms

Choose from a wide variety of the most popular classification, clustering, and regression algorithms. Use classification and regression apps to interactively train, compare, tune, and export models for further analysis, integration, and deployment. If writing code is more your style, you can further optimize models with feature selection and parameter tuning

Automated Machine Learning (AML)

Automatically generate features from training data and optimize models using hyperparameter tuning techniques such as Bayesian optimization. Use specialized feature extraction techniques such as wavelet scattering for signal or image data, and feature selection techniques such as neighborhood component analysis (NCA) or sequential feature selection.

Code Generation


Deploy statistics and machine learning models to embedded systems by generating readable C or C++ code for your entire machine learning algorithm, including preprocessing and post-processing. Update parameters of deployed models without regenerating the C/C++ prediction code. Accelerate verification and validation of your high-fidelity simulations using machine learning models through MATLAB function blocks and system blocks in Simulink®.

Scaling and Performance

Use tall arrays to train machine learning models on data sets too large to fit in machine memory, with minimal changes to your code. You can also speed up statistical computations and model training with parallel computing on your desktop, on clusters, or on the cloud.

Related Resources

Quick start of Machine Learning 


Using Analytics and Machine Learning to Build Intelligent Products and Services

Have Questions About Using MATLAB for Machine Learning

30 Days of Exploration at Your Fingertips

Name, Title

Share the amazing things customers are saying about your business. Double click, or click Edit Text to make it yours.

Baker Hughes

Utilities and Energy

Predictive Maintenance Software for Gas and Oil Extraction Equipment Using Data Analytics and Machine Learning


Neural Bypass Technology Restores Movement to a Paralyzed Man’s Arm and Hand


Helps Clients Achieve Basel II Compliance and Deliver Economic Capital, Risk, and Valuation Models


Banking and Finance

All rights reserved. Copyright © TechSource Systems Pte Ltd.
Company Registration No. 199603163W