Generic Work
Using Recurrent Neural Networks to Judge Fitness in Musical Genetic Algorithms
PublicDownloadable Content
open in viewerWe used a recurrent neural network as a fitness function for a genetic algorithm to generate monophonic solos. The genetic algorithm is based on GenJam as described in Biles (1994). We conducted training sessions with human participants in order to compare and quantify some of the differences between human-feedback and RNN fitness functions. We found that the RNNs can effectively play the role of human fitness feedback, but still suffer in many areas. Our results suggest that certain types of recurrent neural networks can address the issues with human feedback, and thus should be explored in future research.
- Creator
- Keyword
- Date created
- 1/1/17
- Resource type
- Event
- 8th International Conference on Computational Creativity (ICCC)
- Extent
- Rights statement
- Last modified
- 2020-09-22
Relations
- In Collection:
Items
Items
Thumbnail | Title | Visibility | Embargo Release Date | Actions |
---|---|---|---|---|
Using_Recurrent_Neural_Networks_to_Judge_Fitness_in_Musical_Genet.pdf | Public | Download |
Permanent link to this page: https://digital.wpi.edu/show/kh04ds264