During this event, you will learn about the new capabilities available in the MATLAB environment to address some of the major technical challenges in teaching and research.
In the first part of the presentation, you will discover several cloud services available to MATLAB users to enrich their teaching and learning anywhere and anytime, such as
- how to gain instant access to the latest version of MATLAB on the cloud through your web browser
- how to use interactive online trainings to foster your students’ MATLAB and Simulink skills
- how to create your own auto-graded assignments to supplement students’ learning in engineering and science
- how to share code with students and coworkers and data with your students
- how to integrate mobile devices into your learning environment and exercises
The second part of the presentation will focus on practical aspects of the domain of deep learning and demonstrate new MATLAB features that simplify these tasks and eliminate the low-level programming. From prototype to production, we’ll build and train neural networks, and discuss automatically converting a model to CUDA to run natively on GPUs.
Some of the key highlights will include:
- Performing pixel-level semantic segmentation on images
- Importing and use pre-trained models from TensorFlow and Caffe
- Speeding up network training with parallel computing on a cluster
- Using data augmentation to increase the accuracy of a deep learning model
- Automatically converting a model to CUDA to run on GPUs