±¨ ¸æ ÈË£ººú°ü¸Ö ×êÑÐÔ±£¨Öйú¿ÆѧԺ×Ô¶¯»¯×êÑÐËù£©
»ã±¨¹¦·ò£º10ÔÂ11ÈÕ£¨ÖÜÎ壩9:30¡«11:00
»ã±¨µØÖ·£º±¦É½Ð£ÇøÍÆËã»úѧԺ´óÂ¥402ÊÒ
Ñû Çë ÈË£ºÕÅÎä ½ÌÊÚ
»ã±¨ÌáÒª£º
This talk introduces our recent study on Information Theoretical Learning (ITL). By comparing with the conventional performance-based approaches, I will show that ITL presents unique features which have not been reported before in classifications. Two parts of study will be given in the talk, that is:
1. Bayesian classifiers VS. Mutual information classifiers
2. Cost free learning and Abstaining learning
Our findings confirm that ITL provides a new perspective for understanding some learning mechanisms or decision rules in our daily life. I will also present personal viewpoints on the cons and pros of ITL.
»ã±¨È˼ò½é:
ºú°ü¸Ö£¬1993ÄêÓÚ¼ÓÄôóMcMaster University»ñ²©Ê¿Ñ§Î»£¬1994-1997ÄêÓÚ¼ÓÄôóMemorial University of NewfoundlandÈÎÖ°¸ß¼¶×êÑй¤³Ìʦ£¬1997ÄêÖÁ½ñÓÚÖйú¿ÆѧԺ×Ô¶¯»¯×êÑÐËùģʽ¼ø±ð¹ú¶È³Áµã³¢ÊÔÊÒÈÎÖ°×êÑÐÔ±£¬ÆÚ¼äÓÚ2000Ä걻ƸΪÖйú¿ÆѧԺ±±¾©×êÑÐÉúÔº½ÌÊÚ£¬2006Ä걻ƸΪ·¨¹úÖÐÑë°ÍÀ蹤³Ì´óѧ¿Í×ù½ÌÊÚ£¬2009Ä걻ƸΪÖйú¿Æѧ¼¼Êõ´óѧ²©Ê¿Éúµ¼Ê¦£¬ÓÚ2000-2005ÄêÈÎÖ°Öз¨ÐÅÏ¢¡¢×Ô¶¯»¯¡¢ÀûÓÃÊýѧ½áºÏ³¢ÊÔÊÒ£¨LIAMA£©Öз½Ö÷ÈΡ£×êÑз½ÏòÔ̺¬ÖÇÄÜϵͳ¡¢Ä£Ê½¼ø±ð¡¢Ö²Îï³É³¤½¨Ä£¡¢»úе½ø½¨µÈ£¬ÔÚÁìÓòÓйض¥¼¶¹ú¼ÊÆÚ¿¯£¨Ô̺¬IEEE TPAMI, TNN, TKDE, TIP, TSMCµÈ£©£¬¹ú¼Ê»áÒ飨Ô̺¬NIPS, ICML, AAAI, ICDM, CVPRµÈ£©°ä·¢¶àƪÎÄÕ£¬Ôø×÷Ϊ»áÒéÖ÷ϯ»ò·¨Ê½Î¯Ô±»áίԱ²Î¼Ó×éÖ¯¶à¸ö¹ú¼Ê/¹úÄÚ³ÛÃûѧÊõ»áÒ飬²Î¼Ó¶à¸ö¹ú¼Ê/¹úÄÚ¶¥¼¶ÆÚ¿¯µÄÂÛÎÄÆÀÉó¹¤×÷¡£Ä¿Ç°ÎªIEEE¸ß¼¶»áÔ±£¬¡¶×Ô¶¯»¯Ñ§±¨¡·£¬¡¶Ä£Ê½¼ø±ðÓëÈËΪÖÇÄÜ¡·±àί£¬Öйú×Ô¶¯»¯Ñ§»á½ÚÔìÀíÂÛרҵίԱ»á¡¢ÖÇÄÜ×Ô¶¯»¯×¨ÒµÎ¯Ô±»áίԱ£¬ÖйúÈËΪÖÇÄÜѧ»á»úе¸ÐÖªÓëÐé¹¹ÏÖʵרҵίԱ»áίԱ¡£
Ó×ÎÒÖ÷Ò³£ºhttp://liama.ia.ac.cn/wiki/user:hubg:home