TY - JOUR
T1 - Variational temporal abstraction
AU - Kim, Taesup
AU - Ahn, Sungjin
AU - Bengio, Yoshua
N1 - Funding Information:
We would like to acknowledge Kakao Brain cloud team for providing computing resources used in this work. TK would also like to thank colleagues at Mila, Kakao Brain, and Rutgers Machine Learning Group. SA is grateful to Kakao Brain, the Center for Super Intelligence (CSI), and Element AI for their support. Mila (TK and YB) would also like to thank NSERC, CIFAR, Google, Samsung, Nuance, IBM, Canada Research Chairs, Canada Graduate Scholarship Program, and Compute Canada.
Publisher Copyright:
© 2019 Neural information processing systems foundation. All rights reserved.
PY - 2019
Y1 - 2019
N2 - We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state transition hierarchically. We also propose to apply this model to implement the jumpy imagination ability in imagination-augmented agent-learning in order to improve the efficiency of the imagination. In experiments, we demonstrate that our proposed method can model 2D and 3D visual sequence datasets with interpretable temporal structure discovery and that its application to jumpy imagination enables more efficient agent-learning in a 3D navigation task.
AB - We introduce a variational approach to learning and inference of temporally hierarchical structure and representation for sequential data. We propose the Variational Temporal Abstraction (VTA), a hierarchical recurrent state space model that can infer the latent temporal structure and thus perform the stochastic state transition hierarchically. We also propose to apply this model to implement the jumpy imagination ability in imagination-augmented agent-learning in order to improve the efficiency of the imagination. In experiments, we demonstrate that our proposed method can model 2D and 3D visual sequence datasets with interpretable temporal structure discovery and that its application to jumpy imagination enables more efficient agent-learning in a 3D navigation task.
UR - http://www.scopus.com/inward/record.url?scp=85090177438&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090177438&partnerID=8YFLogxK
M3 - Conference article
AN - SCOPUS:85090177438
SN - 1049-5258
VL - 32
JO - Advances in Neural Information Processing Systems
JF - Advances in Neural Information Processing Systems
T2 - 33rd Annual Conference on Neural Information Processing Systems, NeurIPS 2019
Y2 - 8 December 2019 through 14 December 2019
ER -