For people who are already familiar with machine learning and are looking to explore what deep neural networks are, this one-day hands-on course provides an introduction to deep learning. We will cover the basic theory of neural networks, how to implement them using open source libraries, and how to use them to solve classification and regression problems. In this course you will learn to how to build, train, and evaluate deep learning models to predict continuous and discrete quantities using well-tested and freely available Python libraries.
You Will Learn
- What deep learning is and how it revolutionized machine learning in the last few years
- How train a fully connected neural network to solve a classification problem
- How to train a fully connected neural network to solve a regression problem
- How to choose the network architecture, layers, nodes, and loss function
- How a neural network learns using gradient descent and how to tune the learning rate
- How to leverage open source libraries Keras and Tensorflow to build deep learning models
Participants should download and install Miniconda Python 3.7 (https://conda.io/miniconda.html), and they should have access to the Internet during the workshop.