| Paper: | AE-P5.10 | ||
| Session: | Applications to Music II | ||
| Time: | Friday, May 21, 09:30 - 11:30 | ||
| Presentation: | Poster | ||
| Topic: | Audio and Electroacoustics: Applications to Music | ||
| Title: | APPLICATION OF THE MINIMUM FUEL NEURAL NETWORK TO MUSIC SIGNALS | ||
| Authors: | Anders la Cour-Harbo; Aalborg University | ||
| Abstract: | Finding an optimal representation of a signal in an over-complete dictionary is often quite difficult. Since general results in this field are not very application friendly it truly helps to specify the framework as much as possible. We investigate the method Minimum Fuel Neural Network (MFNN) for finding sparse representations of music signals. This method is a set of two ordinary differential equations. We argue that the most important parameter for optimal use of this method is the discretization step size, and we demonstrate that this can be a priori determined. This significantly speeds up the convergence of the MFNN to the optimal sparse solution. | ||
| Back | |||
Home -||-
Organizing Committee -||-
Technical Committee -||-
Technical Program -||-
Plenaries
Paper Submission -||-
Special Sessions -||-
ITT -||-
Paper Review -||-
Exhibits -||-
Tutorials
Information -||-
Registration -||-
Travel Insurance -||-
Housing -||-
Workshops