- Full text PDF available (3)
- This year (0)
- Last 5 years (0)
- Last 10 years (0)
We investigate using gradient descent methods for learning ranking functions; we propose a simple probabilistic cost function, and we introduce RankNet, an implementation of these ideas using a neural network to model the underlying ranking function. We present test results on toy data and on data from a commercial internet search engine.
This thesis investigates how audio analysis techniques and representations can be used to automate the sequencing of arbitrary sounds in order to provide a higher level and more expressive control over the creation of sample based music. This pursuit required the creation of a mosaicing algorithm prototyping language, which expedites the process of creating… (More)