Adaptive Generative Modeling in Resource-Constrained Environments

Jung-Eun Kim1,a, Richard Bradford2, Max Del Giudice1,b and Zhong Shao1,c
1Computer Science Yale University New Haven, CT, USA
ajung-eun.kim@yale.edu
bmax.delgiudice@yale.edu
czhong.shao@yale.edu
2Commercial Avionics Engineering Collins Aerospace Cedar Rapids, IA, USA
richard.bradford@collins.com

ABSTRACT


Modern generative techniques, deriving realistic data from incomplete or noisy inputs, require massive computation for rigorous results. These limitations hinder generative techniques from being incorporated in systems in resource-constrained environment, thus motivating methods that grant users control over the time-quality trade-offs for a reasonable “payoff” of execution cost. Hence, as a new paradigm for adaptively organizing and employing recurrent networks, we propose an architectural design for generative modeling achieving flexible quality. We boost the overall efficiency by introducing non-recurrent layers into stacked recurrent architectures. Accordingly, we design the architecture with no redundant recurrent cells so we avoid unnecessary overhead.



Full Text (PDF)