Florian Colombo

Learn More
A big challenge in algorithmic composition is to devise a model that is both easily trainable and able to reproduce the long-range temporal dependencies typical of music. Here we investigate how artificial neural networks can be trained on a large corpus of melodies and turned into automated music composers able to generate new melodies coherent with the(More)
Human brains can deal with sequences with temporal dependencies on a broad range of timescales, many of which are several order of magnitude longer than neuronal timescales. Here we introduce an artificial intelligence that learns and produces the complex structure of music, a specific type of slow sequence. Our model employs a separation of fundamental(More)
Acknowledgements I sincerely thanks Alex Seeholzer, who supervised my work, for his more than helpful advices and ideas, Klaus Greff from IDSIA, who kindly answered some of my questions about the long short term memory networks and Pr. Wulfram Gerstner, who gave me the opportunity to join my studies with my passion for music. Lausanne, January 2015 F. C. i(More)
  • 1