Entropy-based optimization to trade-off energy and accuracy for activity mobile sensing

Deep neural networks have been remarkable successful in various AI tasks but often cast high computation and energy cost for energy-constrained applications such as mobile sensing. We address this problem by proposing a novel framework that optimizes the prediction accuracy and energy cost simultaneously, thus enabling effective cost-accuracy trade-off at test time. In our framework, each data instance is pushed into a cascade of deep neural networks with increasing sizes, and a selection module is used to sequentially determine when a sufficiently accurate classifier can be used for this data instance. The cascade of neural networks and the selection module are jointly trained in an end-to-end fashion by the REINFORCE algorithm to optimize a trade-off between the computational cost and the predictive accuracy. Our method is able to simultaneously improve the accuracy and efficiency by learning to assign easy instances to fast yet sufficiently accurate classifiers to save computation and energy cost, while assigning harder instances to deeper and more powerful classifiers to ensure satisfiable accuracy. Moreover, we demonstrate our method's effectiveness with extensive experiments on CIFAR-10/100, ImageNet32x32 and original ImageNet dataset.

Download Full-text

A Flow-Preserving Algorithm for the Time-Cost Trade-Off Problem

IIE Transactions ◽

10.1080/05695558208974589 ◽

1982 ◽

Vol 14 (2) ◽

pp. 109-113 ◽

Cited By ~ 4

Author(s):

Suleyman Tufekci

Keyword(s):

Time Cost ◽

Trade Off

Download Full-text

Dual Goals for Speed and Accuracy on the Same Performance Task

Journal of Personnel Psychology ◽

10.1027/1866-5888/a000063 ◽

2012 ◽

Vol 11 (3) ◽

pp. 118-126 ◽

Cited By ~ 3

Author(s):

Olive Emil Wetter ◽

Jürgen Wegge ◽

Klaus Jonas ◽

Klaus-Helmut Schmidt

Keyword(s):

Memory Scanning ◽

Performance Task ◽

Performance Tasks ◽

Trade Off ◽

Test Experiment ◽

Trade Offs ◽

New Finding ◽

Sternberg Paradigm ◽

Speed Accuracy ◽

Speed And Accuracy

In most work contexts, several performance goals coexist, and conflicts between them and trade-offs can occur. Our paper is the first to contrast a dual goal for speed and accuracy with a single goal for speed on the same task. The Sternberg paradigm (Experiment 1, n = 57) and the d2 test (Experiment 2, n = 19) were used as performance tasks. Speed measures and errors revealed in both experiments that dual as well as single goals increase performance by enhancing memory scanning. However, the single speed goal triggered a speed-accuracy trade-off, favoring speed over accuracy, whereas this was not the case with the dual goal. In difficult trials, dual goals slowed down scanning processes again so that errors could be prevented. This new finding is particularly relevant for security domains, where both aspects have to be managed simultaneously.

Download Full-text