Deep Learning with Convolutional Neural Networks: Understand, Develop and Apply

Trainer: Krzysztof Kudryński

Workshop description:

There seems to be a common agreement to treat Deep Learning as a magic blackbox. Developers only need to run `build`, `train` and `apply` methods and the frameworks will do the rest. However, frameworks are much more effective when in hands of a conscious developper. During this workshop we will use all the goodness of frameworks (eg. TensorFlow, Keras) but we will also learn how it works, why it works or if it fails - how to fix it.
 

In this workshop you will:

• gain deep understanding of Convolutional Neural Network - the most common Deep Learning tool at the moment.
• learn how to consciously design it so that it solves your more and more complicated problems
• see how you can reuse publicly available solutions, how to modify them, tune them to your own needs
• learn how to use frameworks like: TensorFlow and Keras to build Deep Learning solutions, monitor their training, and apply them in production.

Experience required: 

To actively participate in the workshop, basic knowledge of Python is required.

Environment: 

You will need your own laptop, with configured environment (git, python3 64-bit with pip, numpy, scipy, opencv-python, matplotlib, tensorflow, keras and pillow). A step-by-step instruction to prepare your environment is available at https://bitbucket.org/alberciak/cnn_4h. (part0_environment/readme)

Language: English

Location: Olivia Business Centre, Olivia Four, O4 Coworking