EENet: Energy Efficient Neural Networks with Run-time Power Management
DescriptionDeep learning approaches, such as convolution neural networks (CNNs), have achieved tremendous success in versatile applications. However, one of the challenges to deploying the deep learning models on resource-constrained systems is its huge energy cost. In this paper, we propose an Energy Efficient Neural Network, which introduces a plug-in module to the state-of-the-art networks by incorporating run-time predictive early exit enabled power management. Extensive experimental results demonstrate that EENet achieves up to 63.8\% energy-saving compared with classic deep learning networks and 21.5\% energy-saving compared with the early exit under state-of-the-art exiting strategies, together with improved timing performance.
TimeThursday, July 13th10:55am - 11:10am PDT
Location3003, 3rd Floor
AI/ML Application and Infrastructure