PRE2016 3 Groep2: Difference between revisions
| Line 15: | Line 15: | ||
== Generative Adversarial Networks == | == Generative Adversarial Networks == | ||
Generative Adversarial Networks (also known as GAN) is a type of machine learning where two neural networks compete against each other. <br> | |||
The two networks consist of one being a generative network, while the other is discriminative. The generative network is trained on data sets to map the distribution of space | |||
== Training Data == | == Training Data == | ||
Revision as of 12:27, 16 February 2017
This is group 2's page
Group Composition
Group 2 has the following members:
- Steven Ge
- Rolf Morel
- Rick Coonen
- Noud de Kroon
- Bas van Geffen
- Jaimini Boender
- Herman Galioulline
Project Description
In this project, we will explore music generation using artificial intelligence. Technically speaking, we will attempt to generate music using a generative adversarial network (GAN) (a technique already proven to work with images. Socially we will also investigate what kind of effect artificial intelligence might have not only on the music industry, but also society's perception of AI being able to generate "art". Furthermore, we will go into whether AI generating music will have a positive or negative effect on not only the industry but also society as a whole.
Generative Adversarial Networks
Generative Adversarial Networks (also known as GAN) is a type of machine learning where two neural networks compete against each other.
The two networks consist of one being a generative network, while the other is discriminative. The generative network is trained on data sets to map the distribution of space
Training Data
- Million Song Dataset
Art Robots
How the art created by robots, will affect art and artists. Having the ability for robots to create art will push the frontier of what robots are capable of and break through into one of the last safe havens of man-only activities.