Article

AI Songsmith Cranks Out Surprisingly Catchy Tunes

via MIT Technology Review

Nov. 30, 2016

People
Groups

Google’s songwriting program learns by combining statistical learning and explicit rules—the same approach may make it easier for engineers to shape other AI programs.

Read on MIT Technology Review
Related Content
Event Events

Natasha Jaques Dissertation Defense

Towards Social and Affective Artificial IntelligenceSocial learning is a crucial component of human intelligence, allowing us to rapidly ...
Video Videos

Natasha Jaques Dissertation Defense

Natasha Jaques defends her dissertation on July 31, 2019.
Publication Research

Sequence Tutor: Conservative Fine-Tuning of Sequence Generation Models with KL-Control

Jaques, N., Gu, S., Bahdanau, D., Hernandez-Lobato, J., Turner, R., and Eck, D. International Conference on Machine Learning (ICML), Sydney, Australia, August 2017.
Publication Research

Intrinsic Social Motivation via Causal Influence in Multi-Agent RL

Jaques, N., Lazaridou, A., Hughes, E., Gulcehre, C., Ortega, P. A., Strouse, D. J., Leibo, J. Z., and de Freitas, N. "Intrinsic Social Motivation via Causal Influence in Multi-Agent RL," International Conference on Representation Learning (ICLR), New Orleans, Louisiana, May 2019 (submitted).