Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification using Convolutional Neural Networks (CNNs). We will also look at regularization techniques and how to deal with under- and over-fitting. All examples will use Python; some familiarity with Python is recommended. Computers will be available to complete exercises. We will run the models using Google Colab, which requires a Google account.

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification using Convolutional Neural Networks (CNNs). We will also look at regularization techniques and how to deal with under- and over-fitting. All examples will use Python; some familiarity with Python is recommended. Computers will be available to complete exercises. We will run the models using Google Colab, which requires a Google account.

Deep Neural Networks (DNNs) are used as a machine learning method for both regression and classification problems. Keras is a high-level, Python interface running on top of multiple neural network libraries, including the popular library TensorFlow. In this workshop, participants will learn how to quickly use the Keras interface to perform nonlinear regression and classification with standard fully-connected DNNs, as well as image classification using Convolutional Neural Networks (CNNs). We will also look at regularization techniques and how to deal with under- and over-fitting. All examples will use Python; some familiarity with Python is recommended.