Introduction to Computer Vision

The introduction of convolutional neural networks (CNNs) has led to dramatic improvements in computer vision tasks.

Data scientists might hesitate to use CNNs in their own work, as deep learning models tend to require vast quantities of training data to create useful models. However, transfer learning is a useful technique that can be used to train your own CNN models even when you have a limited amount of training data. With transfer learning, you can use an existing pretrained CNN, trained on a large database such as ImageNet (http://www.image-net.org/), and fine-tune the pretrained CNN for a related task. In my own past research, I have used the Places CNN trained on the Places2 dataset (a repository of 8 million scene photographs) [1] to create new CNNs to predict the scenicness of an image [2] and classify images of an urban environments for various design features [3].

In this course we will be using Tensorflow/Keras to show you how to work with CNNs, including using an existing CNN to classify an image, as well as using transfer learning to create your own CNN models.