MATLAB Workshop #1 – Deep Learning

Artificial intelligence techniques can be used to solve complex problems related to images, signals, text, and controls. This workshop will help you introduce automation to the products you build and shape how the world does business.

Please sign up at https://forms.gle/Auh6fDwyazc5zw7Q6

In this hands-on workshop, you will write code to:

1. Train deep neural network on GPUs (If GPU is available in your laptop, else it will use CPU for the training)
2. Create deep learning models from scratch for image/signal data.
3. Explore pre-trained models and transfer learning technique.
4. Import and export models from Python frameworks such as Keras and Pytorch. (If time is allowed)
5. Automatically generate code for embedded targets. (If time is allowed)

Prerequisites

Kindly complete these prerequisites before joining the deep learning workshop:

1. Install latest version of MATLAB (2020b onwards)  in your computer with your campus wide license. Kindly inform us if you have difficulties to access the campus wide license.
2. The installed MATLAB should include 8 toolboxes (MATLAB, Parallel Computing Toolbox, Signal Processing Toolbox, System Identification Toolbox, Predictive Maintenance Toolbox, Wavelet Toolbox, Statistics and Machine Learning Toolbox, Deep Learning Toolbox)
3. Install the Add-On Deep Learning Toolbox Model for AlexNet Network and Deep Learning Toolbox Model for GoogLeNet Network
4. Download the workshop material from here:  NUS_MATLAB_DL.zip (2GB of space required)
5. Complete MATLAB Onramp, Image Processing Onramp crash courses (estimated 2 hours for completion). Not only will you get a certificate for each course, but you will also be able to get the most out of this workshop. I strongly encourage you to do this if you are new to MATLAB.