Deep Learning is currently a big & growing trend in data analysis and prediction - and the main fuel of a new era of AI. Google, Facebook and others have shown tremendous success in pushing image, object & speech recognition to the next level.
But Deep Learning can also be used for so many other things! The list of application domains is literally endless.
Although rooted in Neural Network research already in the 1950's, the current trend in Deep Learning is unstoppable, and new approaches and improvements are presented almost every month.
We would like to meet and discuss the latest trends in Deep Learning, Neural Networks and Machine Learning, and reflect the latest developments, both in industry and in research.
The Vienna Deep Learning meetup is positioned at the cross-over of research to industry - having both a focus on novel methods that are published in such a fast pace, and interesting new applications in the startup and industry world. We usually have 2 speakers from either academia, startups or industry, complemented by a "latest news and hot topics" section. Occasionally we do tutorials about software frameworks and how to use Deep Learning in practice. Each evening ends with networking & discussions over drinks and snacks.
Please find all slides of our past meetups, links to photos and some video recordings of our meetups + a wealth of resources to Deep Learning tutorials and more here: https://github.com/vdlm/meetups
Note that this meetup has an intermediate to advanced level (we have done introductions to Deep Learning and neural networks only in the beginning, but try to repeat the most important concepts regularly).
Dear Deep Learners,
Welcome back to the Vienna Deep Learning Meetup talk series after a long break! We will start with a stellar contribution by Sander Dieleman from Google DeepMind London on music generation. Please join us on Thursday, August 20 at 19:00 via Zoom! (Link will be provided to registered participants.)
Generating music in the waveform domain
by Sander Dieleman, Google DeepMind
Almost all research in computational music generation so far has focused on symbolic representations: scores, MIDI sequences and other representations that make abstraction of certain aspects of the music, such as the idiosyncrasies of a particular performance. However, this removes a lot of nuance from the generated content that can be quite important musically, and more importantly, can greatly impact our enjoyment of the music. Generating music directly in the waveform domain is a more challenging task, but it allows us to capture musicality at all scales, from musical form and phrasing all the way down to timbral variations of the instruments. Recent advances in deep learning research have made this approach tractable. In this talk, I will give an overview of the different approaches that have been proposed in the literature and compare them, with a focus on data efficiency, scalability and malleability of the generated audio signals.
The talk will be followed by a Q&A with Sander Dieleman.
As usual, we will also include time for networking - have your favorite drinks and snacks ready :-)
Looking forward to seeing you virtually at the meetup,
Tom, Jan, Alex, René