Location visible to members
Since we started the group we have had a lot of people join who are new to TensorFlow and have asked for us to repeat some of the early intro events. So this month we are starting the first of our Replay Sessions for people who are new to TensorFlow / Deep Learning. This event is generously being supported by SGInnovate.
We've put the MeetUp start time at 6:45pm, so that we can start the talks promptly at 7pm.
Getting Started with the TensorFlow API - Sam Witteveen, Google Developer Expert for Machine Learning
Knowing the key parts of TensorFlow and how to use them can often be confusing at the start. In this talk Sam will go through the basics of TensorFlow and building a model on the newly released TensorFlow 1.4 API. He will show how the various parts of a Deep Learning model work together, how to build a model so it can run on accelerated hardware such as GPUs and TPUs and how to use that model to make predictions on your dataset.
Going Deeper with Transfer Learning - Dr. Martin Andrews, Google Developer Expert for Machine Learning
Martin will describe how Convolutional Neural Networks (CNNs) are used to do image recognition tasks, and then demonstrate a way in which models trained by other people (at great expense) can be leveraged to solve your own image recognition challenges, without breaking the bank. This approach works even if you don't have access to huge datasets or specialised deep learning hardware.
While we don't have spots for lightning talks this month we are actively looking for speakers for our events next year : '30 minutes long-form', and lightning talks where we welcome folks to come up and talk about something cool they've done with TensorFlow and/or Deep Learning for 5-10mins (if you have slides, then #max=10).
The key for the Lightning Talks slot is simply the cool/interesting factor. It doesn't matter whether you're an expert or an enthusiastic beginner: Given the responses we have had, we're sure there are lots of people who would be interested to hear what you've been playing with. Please suggest yourself here :