skip to main content
Goldsmiths - University of London
  • Students, Staff and Alumni
  • Search Students, Staff and Alumni
  • Study
  • Course finder
  • International
  • More
  • Search
  • Study
  • Courses
  • International
  • More
 
Main menu

Primary

  • About Goldsmiths
  • Study with us
  • Research
  • Business and partnerships
  • For the local community
  • Academic departments
  • News and features
  • Events
  • Give to Goldsmiths
Staff & students

Staff + students

  • New students: Welcome
  • Students
  • Alumni
  • Library
  • Timetable
  • Learn.gold - VLE
  • Email - Outlook
  • IT support
  • Staff directory
  • Staff intranet - Goldmine
  • Graduate School - PGR students
  • Teaching and Learning Innovation Centre
  • Events admin
In this section

Breadcrumb navigation

  • Events
    • Degree Shows
    • Black History Month
  • Calendar
Lecture

What can Deep Neural Networks learn from music?


7 Nov 2016, 4:30pm - 5:30pm

Lecture Theatre, Ben Pimlott Building

Event overview

Cost Free. All welcome.
Department Computing , Psychology
Website Whitehead Lecture Series
Contact p.fry(@gold.ac.uk)

Douglas Eck (Google Brain) discusses Magenta, a project to generate music, video, images and text using machine intelligence.

4.30-5.30pm Monday 7 November 2016
Lecture Theatre, Ben Pimlott Building, Goldsmiths

* * * * * * * *

The Magenta Project is an effort to generate music, video, images and text using machine intelligence. The goal of Magenta is to produce open-source tools and models that help creative people be even more creative. Magenta poses the question: “Can machines make music and art? If so, how? And if not, why not?”

(Partial answer: machines won't replace artists or musicians anytime soon, thankfully!)

In this edition of the Whitehead Lecture Series, Douglas Eck (Research scientist at Google Brain) gives an overview of Magenta with focus on closing the loop between musicians and code. He'll discuss recent progress in audio and music score generation, and will focus on the challenge of improving machine learning generative models based on user and artist feedback.

Bio: Douglas Eck is a research scientist at Google working in the areas of music and machine learning. Currently he is leading the Magenta Project, a Google Brain effort to generate music, video, images and text using deep learning and reinforcement learning. One of the primary goals of Magenta is to better understand how machine learning algorithms can learn to produce more compelling media based on feedback from artists, musicians and consumers. Doug led the Search, Recommendations and Discovery team for Play Music from the product's inception as Music Beta by Google through its launch as a subscription service.

Before joining Google in 2010, Doug was an Associate Professor in Computer Science at University of Montreal (MILA lab) where he worked on rhythm and meter perception, machine learning models of music performance, and automatic annotation of large audio data sets.

* * * * * * * *

http://research.google.com/pubs/author39086.html
https://magenta.tensorflow.org

* * * * * * * *

Whitehead Lecture Series

Dates & times

Date Time Add to calendar
7 Nov 2016 4:30pm - 5:30pm
  • apple
  • google
  • outlook

Accessibility

If you are attending an event and need the College to help with any mobility requirements you may have, please contact the event organiser in advance to ensure we can accommodate your needs.

Event controls

  • About us
  • Accessibility statement
  • Contact us
  • Cookie use
  • Find us
  • Copyright and disclaimer
  • Jobs
  • Modern slavery statement
Admin login
  • Twitter
  • Linkedin
  • TikTok
  • Instagram
  • YouTube
© Goldsmiths, University of London Back to top