In universities and colleges around the world, Google has encouraged the creation of "Google Developer Student Clubs". To round out the year, Sam Witteveen and I decided to offer our three-part "Back-to-Basic" series to clubs in the South-East Asia region, to introduce them to TensorFlow and Deep Learning.
This session was the second in the three-part series, and focused on Deep Learning for computer vision using CNNs.
Our presentation was in two parts:
My initial talk, that :
- Gave a brief outline of the use-cases for Deep Learning for vision tasks
- Introduced two new Layers : Conv2d and MaxPool2d
- Tantalised the group with 'Representation Learning ... Transfer Learning'
Sam did a Code-Along using Google Colab, where he lead the audience through :
- Loading and preparing a dataset beyond MNIST
- Building and Training a simple CNN model in Keras
- Doing some analysis of the model outputs
The slides for my talk are here :
If there are any questions about the presentation please ask below, or contact me using the details given on the slides themselves.