A neural network is model composed of many parameters. Although neural networks have achieved huge success, it is challenging to interpret\/explain a trained neural network. The major focus of our research is to interpret\/explain neural networks and apply the interpretation\/explanation to improve training and solve real-world problems.<\/p>\n\n\n\n
<\/p>\n\n\n\n
Sensitivity Analysis<\/strong><\/p>\n\n\n\n A trained neural network builds an input-output mapping based on many parameters. We attempt to explain this implicit mapping by using sensitivity analysis. The sensitivity is usually defined as the output change degree due to input\/parameter change. High sensitivity indicates the output is very sensitive to input\/parameter perturbations. Sensitivity analysis provides the tool for adjusting and interpreting neural networks. <\/p>\n\n\n\n Citation<\/p>\n\n\n\n <\/p>\n\n\n\n Graph Neural Networks<\/strong><\/p>\n\n\n\n We propose a general training strategy to improve graph autoencoder training. This strategy injects noise to training input data. It can fit almost all existing autoencoders.<\/p>\n\n\n\n Citation<\/p>\n\n\n\n <\/p>\n\n\n\n Uncertainty Quantification<\/strong><\/p>\n\n\n\n Machine learning models can predict\/classify well on many cases but very badly on some cases. Therefore, we need to measure uncertainty of specific predictions\/classifications, which can not be replaced by the overall accuracy. However, most conventional machine learning models do not allow us to directly measure uncertainties. Here, we present a strategy for uncertainty quantification.<\/p>\n\n\n\n Citation<\/p>\n\n\n\n <\/p>\n\n\n\n <\/p>\n","protected":false},"excerpt":{"rendered":" A neural network is model composed of many parameters. Although neural networks have achieved huge success, it is challenging to interpret\/explain a trained neural network. The major focus of our research is to interpret\/explain neural networks and apply the interpretation\/explanation to improve training and solve real-world problems. Sensitivity Analysis A trained neural network builds an […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":76,"menu_order":3,"comment_status":"closed","ping_status":"closed","template":"","meta":{"nf_dc_page":"","om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_uf_show_specific_survey":0,"_uf_disable_surveys":false,"_jetpack_hide_featured_image":false,"_jetpack_featured_image_duplicate_dismissed":0,"nfd_onboarding_generated":"","footnotes":""},"class_list":["post-253","page","type-page","status-publish","hentry"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n
\n
\n