TensorFlow has risen in recent years to become one of the most popular and capable machine learning frameworks available, but with so much hyperbole and publicity it can be difficult to understand what it does, why you might want to use it, and how you can get started on something relevant and useful without wasting months or breaking the bank.
In this talk we will use examples in Python to explore some of the core components in the TensorFlow framework and how we use them to quickly train our own models to make predictions. We will build on those examples to look at some performance and scalability challenges that arise with larger and more sophisticated models, and how TensorFlow can address these with the application of distributed computing resources and specialised computing units such as GPUs and TPUs.
By the end of this session you will have a better understanding of how and when to make use of this hugely powerful and flexible framework, and hopefully some of the background you will need to support your journey into machine learning with TensorFlow.
Required audience experience
No prior knowledge of TensorFlow or machine learning necessary.
Objective of the talk
Delegates will hopefully come away from this talk with a broad understanding of what TensorFlow is, the problems that it helps to address, where it adds value and where it gets in the way.
You can view David’s slides and presentation below: