主题

《Automated Building of Deep-Learning Models: an Expand-and-ReduceMethod》

主讲嘉宾

Chuanhai Liu教授

时间

2017年12月20日下午3:00-4:00

地点

行政东楼前座412会议室

主办单位

经济与统计学院及岭南统计科学研究中心

讲座内容简介

Big data analysis demands computer-intensive data-driven methods more than ever for exploring and modeling complex data structures. Because of its capability and flexibility torepresent complex local and global data structures, ``multi-level nets'' orDeep Learning models can be practically very useful. However, architecture configuration and parameter optimization of such models are extremely challenging, both statistically and computationally. To overcome the difficulty,we propose an Expand-and-Reduce method for automated building of Deep-Learning models. The purpose of the method is three-fold: 1) it generates models for Artificial Intelligence-type of applications, 2) it can be used to doconfirmatory-type analysis for investigating prior knowledge-based constructionof network structures, and 3) it provides as a tool for in-depth investigationand understanding of data from scientific inference perspective. With simpleexamples, we show that our proposed method is promising to serve its purpose.