[et_pb_section fb_built=”1″ admin_label=”section” _builder_version=”3.22″][et_pb_row _builder_version=”3.22.1″ border_color_all=”#3255c9″ border_style_all=”groove”][et_pb_column type=”1_4″ _builder_version=”3.22.1″][et_pb_text _builder_version=”3.22.1″ min_height=”11px” custom_margin=”||-25px|||” custom_padding=”||0px|||”]<\/p>\n
Shen Liang<\/strong> <\/p>\n <\/p>\n [\/et_pb_text][et_pb_social_media_follow _builder_version=”3.22.1″ custom_margin=”|||0px”][et_pb_social_media_follow_network social_network=”linkedin” url=”https:\/\/www.linkedin.com\/in\/liang-shen-76a669273\/” _builder_version=”3.22.1″ background_color=”#007bb6″ follow_button=”off” url_new_window=”on”]linkedin[\/et_pb_social_media_follow_network][\/et_pb_social_media_follow][et_pb_divider color=”#3255c9″ _builder_version=”3.22.1″][\/et_pb_divider][et_pb_text _builder_version=”3.22.1″ custom_padding=”0px|||||”]<\/p>\n Dr Shen Liang [\/et_pb_text][\/et_pb_column][et_pb_column type=”3_4″ _builder_version=”3.22.1″][et_pb_text _builder_version=”3.22.1″ custom_margin=”|||||” custom_padding=”0px|||||”]<\/p>\n In real-world applications, deep learning models are often faced with challenges from multi-source data with heterogeneous features. For example, in biomedicine, electrocardiography (ECG) signals of different patients can differ drastically even if they suffer from the same heart condition, thus a computer-aided diagnosis model that works well for one patient may work poorly for another; in astrophysics, simulation is widely used for neutrino event reconstruction, yet the distribution of simulated data often fails to align with that of real data, thus an event reconstruction model trained on simulated data may not be trustworthy on real data. Two effective solutions to the problem with multi-source data are domain adaptation and domain generalization. Domain adaptation attempts to transfer a model trained on one or multiple data sources to a data source where some data is already available, while domain generalization attempts to generalize a model training on multiple data sources to unknown future data. In this seminar, I will introduce some of the most commonly used methodologies for domain adaptation and generalization, and provide suggestions on when to and when not to apply these techniques in the face of multi-source data. Note that this seminar requires the audience to have basic knowledge on transfer learning and multi-task learning, which can be found in the seminar on June 18th.<\/p>\n [\/et_pb_text][et_pb_video_slider _builder_version=”3.22.1″][et_pb_video_slider_item src=”https:\/\/www.youtube.com\/watch?v=bWC9HoAr61g” src_webm=”https:\/\/www.youtube.com\/watch?v=bWC9HoAr61g” _builder_version=”3.22.1″ show_image_overlay=”off”][\/et_pb_video_slider_item][\/et_pb_video_slider][\/et_pb_column][\/et_pb_row][\/et_pb_section][et_pb_section fb_built=”1″ _builder_version=”3.22.1″][et_pb_row _builder_version=”3.22.1″][et_pb_column type=”1_3″ _builder_version=”3.22.1″][\/et_pb_column][et_pb_column type=”2_3″ _builder_version=”3.22.1″][\/et_pb_column][\/et_pb_row][et_pb_row custom_margin=”120px||” _builder_version=”3.22.1″ locked=”off”][et_pb_column type=”4_4″ _builder_version=”3.0.47″][et_pb_divider _builder_version=”3.22.1″][\/et_pb_divider][et_pb_text admin_label=”\u00c0 lire aussi” _builder_version=”3.22.1″ z_index_tablet=”500″]<\/p>\n [\/et_pb_text][et_pb_blog posts_number=”4″ include_categories=”67″ show_author=”off” show_date=”off” show_pagination=”off” module_id=”page_type_blog” _builder_version=”3.22.1″ header_level=”h4″ border_width_bottom_fullwidth=”1px” border_color_bottom_fullwidth=”rgba(51,51,51,0.18)” custom_padding=”||50px|” z_index_tablet=”500″][\/et_pb_blog][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":" Shen LiangOctober 19, 4 PM (Central Eastern Time)online (zoom) Dr Shen Liang(Universit\u00e9 Paris Cit\u00e9, diiP)Shen Liang is a research associate at the Data Intelligence Institute of Paris (diiP) and affiliated with the Universit\u00e9 Paris Cit\u00e9. He has worked on a variety of data management and mining problems including time series analysis, semi-supervised learning, knowledge-guided… Lire la suite Shen Liang – Deep Domain Adaptation and Generalization<\/span><\/a><\/p>\n","protected":false},"author":560,"featured_media":2263,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"","_et_gb_content_width":"","footnotes":""},"categories":[55,1,67],"tags":[],"class_list":["post-2842","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-55","category-diip","category-seminars-hands-on-workshops"],"_links":{"self":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts\/2842","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/users\/560"}],"replies":[{"embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/comments?post=2842"}],"version-history":[{"count":16,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts\/2842\/revisions"}],"predecessor-version":[{"id":3208,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/posts\/2842\/revisions\/3208"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/media\/2263"}],"wp:attachment":[{"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/media?parent=2842"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/categories?post=2842"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wordpress-test.app.u-pariscite.fr\/diip\/wp-json\/wp\/v2\/tags?post=2842"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
October 19, 4 PM (Central Eastern Time)
online (zoom)<\/span><\/p>\n
(Universit\u00e9 Paris Cit\u00e9, diiP)
Shen Liang is a research associate at the Data Intelligence Institute of Paris (diiP) and affiliated with the Universit\u00e9 Paris Cit\u00e9. He has worked on a variety of data management and mining problems including time series analysis, semi-supervised learning, knowledge-guided deep learning and GPU-accelerated computation within various fields such as healthcare, manufacturing, geosciences and astrophysics. He holds a PhD in software engineering from Fudan University, China.<\/span><\/p>\nAbstract<\/strong><\/h3>\n
Other seminars
<\/span><\/h2>\n