Deep learning capabilities expanded in latest MATLAB and Simulink software release
Release 2018b of MATLAB and Simulink software from MathWorks contains significant enhancements for deep learning, along with new capabilities and bug fixes across the product families.
Release 2018b of MATLAB and Simulinksoftware from MathWorks contains significant enhancements for deep learning, along with new capabilities and bug fixes across the product families. One new feature is the Deep Learning Toolbox, which replaces Neural Network Toolbox and provides users with a framework for designing and implementing deep neural networks. Now, according to the company, image processing, computer vision, signal processing, and systems engineers can use MATLAB to more easily design complex network architectures and improve the performance of their deep learning models.
Additionally, release 2018b features the new Deep Network Designer app, which enables users to create complex network architectures or modify complex pretrained networks for transfer learning, and the new ONNX converter, which provides the ability to import and export models from supported frameworks such as PyTorch, MxNet, and TensorFlow. The release also provides a curated set of reference models that are accessible with a single line of code, improved network training, and broadened support for domain-specific workflows.
To Learn More:
Headquarters: Natick, MA, USA
Product: MATLAB and Simulink software
Key Features: Deep Learning Toolbox, Deep Network Designer app, ONNX converter, curated set of reference models accessible with a single line of code.
What MathWorks says:
View more information on the updates.