Yuhang Song
Biography
I am a DPhil candidate in Computer Science at the University of Oxford, doing interdisciplinary research between Artificial Intelligence and Neural Science, supervised by Professor Thomas Lukasiewicz in Intelligent Systems Lab, Professor Rafal Bogacz in Brain Network Dynamics Unit. Before that, I receive my Bachelor's degree at Beihang University, China. I was a research visitor during summer 2017 with Professor Michael L. Littman in HCRI Lab. For more information on Yuhang Song, move to my new homepage.
Selected Publications
-
Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi−Task Learning.
Yuhang Song‚ Mai Xu and Songyang Zhang.
In Proceedings of the 32nd Annual Conference on Neural Information Processing Systems‚ Deep RL Symposium‚ NIPS 2018‚ Montreal‚ Canada.. December, 2018..
Details about Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi−Task Learning. | BibTeX data for Generalization Tower Network: A Novel Deep Neural Network Architecture for Multi−Task Learning.
-
Can the Brain Do Backpropagation? — Exact Implementation of Backpropagation in Predictive Coding Networks
Yuhang Song‚ Thomas Lukasiewicz‚ Zhenghua Xu and Rafal Bogacz
In Proceedings of the 34th Annual Conference on Neural Information Processing Systems‚ NeurIPS 2020‚ December 6–12‚ 2020. December, 2020.
Details about Can the Brain Do Backpropagation? — Exact Implementation of Backpropagation in Predictive Coding Networks | BibTeX data for Can the Brain Do Backpropagation? — Exact Implementation of Backpropagation in Predictive Coding Networks
-
Mega−Reward: Achieving Human−Level Play without Extrinsic Rewards
Yuhang Song‚ Jianyi Wang‚ Thomas Lukasiewicz‚ Zhenghua Xu‚ Shangtong Zhang‚ Andrzej Wojcicki and Mai Xu
In Vincent Conitzer and Fei Sha, editors, Proceedings of the 34th National Conference on Artificial Intelligence‚ AAAI 2020‚ New York‚ New York‚ USA‚ February 7–12‚ 2020. AAAI Press. February, 2020.
Details about Mega−Reward: Achieving Human−Level Play without Extrinsic Rewards | BibTeX data for Mega−Reward: Achieving Human−Level Play without Extrinsic Rewards