Oliver Zeigermann will be at the new ML and AI Conference in London this October. With the following two sessions:
The main language for machine learning has been Python for quite a while and the platform for training models has been servers, preferably with many powerful GPUs.
The browser can also be a platform for making interferences or predictions based on models that have been trained offline by much more powerful machines. This can be helpful to bring machine learning to a zero installation environment and thus closer to potential non technical user.
In this talk Oliver will introduce you to the TensorFlow Playground that helps to understand how machine learning with deep neural networks works. To better understand how specific neural networks make their inferences, there are also some great browser based visualizations, among them ConvNet.js and tsne.js. We will also have a look at them. Finally, you will see how to make inferences in the browser using real Keras based models that can even make use of GPUs.
„Workshop – Introduction to Neural Networks using TensorFlow and Keras“
In this workshop you will learn how Neural Networks work and how you can apply them to the task of image classification using Supervised Learning. This will be illustrated by an example using real pictures of German speed limit signs which we will process with TensorFlow and Keras as a frontend.
Oliver will provide you with a Junyper notebook so you can follow along without installation or try out the examples later at home.
follow us on Twitter – @embarced