PhD THESIS
EPFL, Laboratory of Computational Neuroscience
Learning music composition with recurrent neural networks
SMC 19
16th Sound and Music Computing Conference
Colombo, F., & Gerstner, W. (2019). Learning to Generated Music with BachProp. In Sound and Music Computing Conference.
CCN 17
Annual Conference on Cognitive Computational Neuroscience (CCN)
September 6-8, 2017
Colombo, F., & Gerstner, W. (2017). BachProp: A Trainable Generative Model of Music Scores. In Conference on Cognitive Computational Neuroscience.
EvoMUSART 17
6th International Conference on Computational Intelligence in Music, Sound, Art and Design.
Colombo, F., Seeholzer, A., & Gerstner, W. (2017, April). Deep Artificial Composer: A Creative Neural Network Model for Automated Melody Generation. In International Conference on Evolutionary and Biologically Inspired Music and Art (pp. 81-96). Springer, Cham.
*Best paper award candidate
CSMC 16
1st Conference on Computer Simulation of Musical Creativity
Colombo, F., Muscinelli, S. P., Seeholzer, A., Brea, J., & Gerstner, W. (2016). Algorithmic composition of melodies with deep recurrent neural networks. arXiv preprint arXiv:1606.07251.
Master thesis
Ecole Polytechnique Federale de Lausanne (EPFL)
Colombo, F. F. (2015). Music Learning with Long Short Term Memory Networks (No. EPFL-STUDENT-218541).