Computer Science – Learning
Scientific paper
2011-03-15
Computer Science
Learning
Scientific paper
This paper describes two applications of conditional restricted Boltzmann machines (CRBMs) to the task of autotagging music. The first consists of training a CRBM to predict tags that a user would apply to a clip of a song based on tags already applied by other users. By learning the relationships between tags, this model is able to pre-process training data to significantly improve the performance of a support vector machine (SVM) autotagging. The second is the use of a discriminative RBM, a type of CRBM, to autotag music. By simultaneously exploiting the relationships among tags and between tags and audio-based features, this model is able to significantly outperform SVMs, logistic regression, and multi-layer perceptrons. In order to be applied to this problem, the discriminative RBM was generalized to the multi-label setting and four different learning algorithms for it were evaluated, the first such in-depth analysis of which we are aware.
Bengio Yoshua
Larochelle Hugo
Mandel Michael
Pascanu Razvan
No associations
LandOfFree
Autotagging music with conditional restricted Boltzmann machines does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Autotagging music with conditional restricted Boltzmann machines, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Autotagging music with conditional restricted Boltzmann machines will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-138435