报告题目：Discriminative Restricted Boltzmann Machine for Invariant Pattern Recognition

报告时间: 12月6日，星期四，上午9:30-10:20

报告地点: 北五楼 319

报告人：姬楠楠博士，长安大学理学院数学与信息科学系

报告摘要：

How to make a machine automatically achieve invariant pattern recognition like human brain is still very challenging in machine learning community. In this report, we present a single hidden-layer network TIClassRBM for invariant pattern recognition. In our model, invariant feature extraction and pattern classification can be implemented simultaneously. The mapping from input features to class label is represented by two groups of weights: transformed weights that connect hidden units to data, and pooling weights that connect pooling units yielded by probabilistic max pooling to class label. All weights play an important role in the invariant pattern recognition. The experimental studies on the variations of MNIST and NORB datasets demonstrate that the proposed model yields the best performance among some comparative models.

报告人简介：

姬楠楠，女，陕西渭南人，博士。于2014年12月在西安交通大学数学与统计学院获博士学位，现为长安大学理学院数学与信息科学系教师。长期从事深度学习模型构建、算法设计和应用方面的研究，主持国家自然科学基金青年项目1项、陕西省青年人才项目1项、中央高校基金项目1项，参与国家自然科学基金重大研究计划1项、重点基金1项、青年基金2项、专向基金1项；先后在“Pattern Recognition”、“Neurocomputing”、“Knowledge-Based Systems”、“Pattern Recognition Letters”等一系列国际和国内著名学术刊物发表论文20余篇，SCI索引论文15篇。论文曾获“徐宗本应用数学论文奖”、“陕西省数学会青年优秀论文奖”和“西安交通大学校优秀博士学位论文”。