Deep Learning with PyTorch for more Fun and Profit (Part II)
There are all these great articles and blog posts about Deep Learning describing all that awesome stuff. - Is it all that easy? Let's check! We'll look into: style transfer (making a picture look like painting), speech generation (like Siri or Alexa) and text generation (writing a story). In this talk I'll describe the whole journey: A fun ride from the idea to the very end including all the struggles, failures and successes.
Scheduled on thursday 10:30 in room media
Speaker
Alexander' professional career was always about digitalisation: starting from vinyl records in the nineties to to advanced data analytics nowadays. He's program chair of Europe's main Python conference EuroPython, one of the 25 mongoDB masters, organiser of PyConDE 2017 and a regular contributor to the tech community. He has spoken at many international conferences in Silicon Valley, New York, London, Florence or Paris. He's a partner at Königsweg consultancy for digitalisation, high-tech and data science.
Description
There are all these great blog posts about Deep Learning describing all that awesome stuff. - Is it all that easy? Let's check! This is part 2 of on ongoing series of adventures in Deep Learning for fun, research and business.
We'll look into: style transfer (making a picture look like painting), speech generation (like Siri or Alexa) and text generation (writing a story). In this talk I'll describe the whole journey: A fun ride from the idea to the very end including all the struggles, failures and successes. Steps, we'll cover:
- The data challenge: get the data ready
- Have it run on your Mac with PyTorch and an eGPU
- Creating a character-level language models with an Recurrent Neural Network
- Creating a text generator
- Creating artwork