Deep Learning with JavaScript

Our next event will showcase two speakers covering some great topics around AI and JavaScript. Location TBC!

6.15pm Doors, pizza, drinks
7pm Oliver Ziegermann ‘Leveraging TensorFlow.js to Improve User Experience’
7.50pm Sean Tracey ‘Audio Classification with Keras and JavaScript’

'Leveraging TensorFlow.js to Improve User Experience'
Oliver Zeigermann @DJCordhose
Oliver is a developer and consultant from Hamburg, Germany. He has been involved with AI since his studies in the 90s and has written several books and has recently published the "Deep Learning Crash Course" with Manning. More on http://zeigermann.eu/

In typical offline scenarios with a fixed set of data, machine learning on powerful servers is the way to go. Yet, when dealing with interactive Single Page Applications, zero installation, low latency and high privacy concerns change the story towards machine learning in the browser with TensorFlow.js.

In this talk, we'll learn to train RNN, LSTM, and GRU based models in the browser using mouse movements to infer which button the user is going to click. We will discuss potential applications, including highlighting of buttons for easier access and help with complex flows.

'Audio Classification with Keras and JavaScript'
Sean Tracey @seanmtracey
Sean is a Developer Advocate for IBM. He spends his time putting together new and shiny things to see what's possible with IoT, AI, and Cloud Computing.

Convolutional Neural Networks are the darling of the image recognition world, but did you know that with a little bit of tweaking you can use those same networks to classify sounds too? In this talk, we'll go over the methods and gotchas for processing audio files to work with a CNN.