3月29日:C. L. Philip Chen
发布时间:2018-03-23  阅读次数:2605

告题目:Broad Learning (宽度学习): A paradigm shift in discriminative incremental learning

人:C. L. Philip Chen  Professor

人:陈仪香教授

报告时间:2018329日(周四)14:00-15:30

报告地点:中北校区数学馆201报告厅

 

 

报告人简介:

陈俊龙( C. L. Philip Chen)博士,我国自动化学会副理事长,澳门科协副会长,澳门大学讲座教授,科技学院前院长。 陈教授是IEEE Fellow,美国科学促进会AAAS Fellow, 国际系统及控制论科学院 IASCYS 院士,香港工程师学会 Fellow。陈教授现任 IEEE系统人机及智能学会的期刊主编,曾任该学会国际总主席(2012-2013)。陈教授主要科研在智能系统与控制,计算智能,混合智能,数据科学方向。在2018年 3 月Web of Science “计算机科学学科” 高被引用文章数目学者中 世界排名在前 14名。详见  https://orcid.org/0000-0001-5451-7230 。陈教授获 IEEE 学会颁发了 4次杰出贡献奖,2017 TNNLS Outstanding Paper Award。 他是美国工学技术教育认证会( ABET)的评审委员。澳门大学工程学科及计算机工程获得国际【华盛顿协议】的认证是陈教授对澳门工程教育的至高贡献。担任院长期间带领澳门大学的工程学科及计算机学科双双进入世界大学学科排名前200名。2016年他获得了母校,美国普度大学,的杰出电机及计算机工程奖。

 

报告摘要:

In recent years, deep learning caves out a research wave in machine learning. With outstanding performance, more and more applications of deep learning in pattern recognition, image recognition, speech recognition, and video processing have been developed. 

The talk is to introduce “Broad Learning” – a complete paradigm shift in discriminative learning and a very fast and accurate learning without deep structure. The broad learning system (BLS) utilizes the power of incremental learning. That is without stacking the layer-structure, the designed neural networks expand the neural nodes broadly and update the weights of the neural networks incrementally when additional nodes are needed and when the input data entering to the neural networks continuously. The designed network structure and incremental learning algorithm are perfectly suitable for modeling and learning big data environment. Experiments indicate that the designed structure and algorithm out-perform existing structures and learning algorithms. Several BLS variations that cover existing deep-wide/broad-wide structures will be discussed.

金沙直营网
www.socialprepa.com Copyright Software Engineering Institute
院长信箱:yuanzhang@socialprepa.com | 院办电话:021-62232550 | 学院地址:上海中山北路3663号理科大楼