The main tasks involved in deep learning are to assemble large data sets, create a neural network, to train, visualize, and evaluate different models, using specialized hardware – often requiring unique programming knowledge. These tasks are frequently even more challenging because of the complex theory behind them.
In this hands‑on lab, you will use MATLAB® in the Open OnDemand environment to:
- Train deep neural networks on GPUs at the HCC.
- Create deep learning models from scratch for image and signal data.
- Explore pretrained models and use transfer learning.
- Perform classification tasks on images and signals.
- Explore some example deep learning applications such as ECG classification and pixel‑level semantic segmentation on images.