This event is co-hosted with the Ann Arbor Machine Learning Meetup group.
In this tutorial, you will learn how to use the open-source TensorFlow library for deep learning. What's so great about TensorFlow is that it allows us to work with multi-dimensional arrays and train deep neural network very efficiently by utilizing GPU resources.
In this introduction to TensorFlow, you will learn how to define computational graphs and how to execute them in a Python runtime environment. After implementing backpropagation for a simple multi-layer perceptron, we will talk about TensorFlow's convenience features for optimization and the new layers API to construct more complex deep learning architectures more compactly. Finally, we will implement a General Adversarial Networks architecture to see how we can access and update variables from different network graphs and scopes -- the entry point for inventing and experimenting with novel architectures in our real-world applications and research.
As a Ph.D. candidate at Michigan State University, Sebastian Raschka is developing novel computational methods in the field of computational biology. Among others, his research activities include the development of new deep learning architectures to solve problems in the field of biometrics.
Among his other works is his book “Python Machine Learning,” a bestselling title at Packt and on Amazon.com, which has been translated into German, Korean, Chinese, Japanese, and Italian. In his free time, Sebastian loves to contribute to open source projects, and methods that he implemented are now successfully used in machine learning competitions such as Kaggle.