Timezone: »

 
Poster
Sequential Neural Processes
Gautam Singh · Jaesik Yoon · Youngsung Son · Sungjin Ahn

Tue Dec 10 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #132
in Deep Learning -- Generative Models »

Neural Processes combine the strengths of neural networks and Gaussian processes to achieve both flexible learning and fast prediction in stochastic processes. However, a large class of problems comprise underlying temporal dependency structures in a sequence of stochastic processes that Neural Processes (NP) do not explicitly consider. In this paper, we propose Sequential Neural Processes (SNP) which incorporates a temporal state-transition model of stochastic processes and thus extends its modeling capabilities to dynamic stochastic processes. In applying SNP to dynamic 3D scene modeling, we introduce the Temporal Generative Query Networks. To our knowledge, this is the first 4D model that can deal with the temporal dynamics of 3D scenes. In experiments, we evaluate the proposed methods in dynamic (non-stationary) regression and 4D scene inference and rendering.

Keywords: Generative Models · Deep Learning · Algorithms -> Meta-Learning; Algorithms -> Representation Learning; Applications · Visual Scene Analysis and Interpretation; D
[ Paper]  [ Slides] 

Author Information

Gautam Singh (Rutgers University)

I am starting my second year as a Ph.D. student at the Department of Computer Science at Rutgers University. My focus area is probabilistic generative models. Prior to this, I worked at IBM Research India for 3 years after finishing my undergrad from IIT Guwahati.

Jaesik Yoon (SAP)
Youngsung Son (Electronics and Telecommunications Research Institute)
Sungjin Ahn (Rutgers University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors