AnytimeNet: Controlling Time-Quality Tradeoffs in Deep Neural Network Architectures
Jung-Eun Kim1,a, Richard Bradford2,b and Zhong Shao1,c
1Computer Science Yale University New Haven, CT, USA
2Commercial Avionics Engineering Collins Aerospace Cedar Rapids, IA, USA
ajung-eun.kim@yale.edu
brichard.bradford@collins.com
czhong.shao@yale.edu
ABSTRACT
Deeper neural networks, especially those with extremely large numbers of internal parameters, impose a heavy computational burden in obtaining sufficiently high-quality results. These burdens are impeding the application of machine learning and related techniques to time-critical computing systems. To address this challenge, we are proposing an architectural approach for neural networks that adaptively trades off computation time and solution quality to achieve high-quality solutions with timeliness. We propose a novel and general framework, AnytimeNet, that gradually inserts additional layers, so users can expect monotonically increasing quality of solutions as more computation time is expended. The framework allows users to select on the fly when to retrieve a result during runtime. Extensive evaluation results on classification tasks demonstrate that our proposed architecture provides adaptive control of classification solution quality according to the available computation time.
Keywords: Cyber-physical System, Time-Quality Tradeoff, Time-Critical System, Adaptive Neural Network, Machine Learning.
