HMC: A Hybrid Reinforcement Learning Based Model Compression for Healthcare Applications
2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)(2019)
摘要
Artificial intelligence (AI) healthcare applications to optimize workflows, reduce costs while focusing on patient care are on the rise. While deeper and wider neural networks are designed for complex healthcare applications, model compression is poised to be an effective way to deploy networks on medical devices that often have hardware and speed constraints. Most state-of-the-art model compression techniques require a resource centric manual process that explores a large space to find a trade-off solution between model size and accuracy. Recently, reinforcement learning (RL) approaches are proposed to automate such hand-crafted process. However, most RL model compression algorithms are model-free, meaning a very long time to train such RL agents due to the huge state space. In this work, we develop a hybridRL model compression (HMC) method that integrates model-based and model-free RL approaches. We demonstrate our method on a wide range of imaging data on healthcare related model architectures. Compared to model-free RL approaches, our results show that HMC method reduces the training time significantly, exhibits better generalization capabilities across different data sets, and preserves comparable model compression performance.
更多查看译文
关键词
complex healthcare applications,speed constraints,resource centric manual process,reinforcement learning approaches,hand-crafted process,RL model compression algorithms,RL agents,huge state space,hybridRL model compression method,model-free RL approaches,healthcare related model architectures,HMC method,hybrid reinforcement,artificial intelligence healthcare applications,model compression performance,neural networks,generalization capabilities,imaging data
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要