| Paper ID | C-2-3.1 |
| Paper Title |
MERGING WELL-TRAINED DEEP CNN MODELS FOR EFFICIENT INFERENCE |
| Authors |
Cheng-En Wu, Jia-Hong Lee, Timmy S.T. Wan, Yi-Ming Chan, Chu-Song Chen, Academia Sinica, Taiwan |
| Session |
C-2-3: Machine Learning and Data Analysis 1 |
| Time | Wednesday, 09 December, 17:15 - 19:15 |
| Presentation Time: | Wednesday, 09 December, 17:15 - 17:30 Check your Time Zone |
|
All times are in New Zealand Time (UTC +13) |
| Topic |
Machine Learning and Data Analytics (MLDA): |
| Abstract |
In signal processing applications, more than one tasks often have to be integrated into a system. Deep learning models (such as convolutional neural networks) of multiple purposes have to be executed simultaneously. When deploying multiple well-trained models to an application system, running them simultaneously is inefficient due to the collective loads of computation. Hence, merging the models into a more compact one is often required, so that they can be executed more efficiently on resource-limited devices. When deploying two or more well-trained deep neural-network models in the inference stage, we introduce an approach that fuses the models into a condensed model. The proposed approach consists of three phases: FilterAlignment, Shared-weight Initialization, and Model Calibration. It can merge well-trained feed-forward neural networks of the same architecture into a single network to reduce online storage and inference time. Experimental results show that our approach can improve both the run-time memory compression ratio and increase the computational speed in the execution. |