Dual Learning Tutorial

IJCAI 2019 Tutorial on Dual Learning for Machine Learning Macao, China August 10th, 2019 Speakers Tao QinMSRA Yingce XiaMSRA Abstract Many AI tasks are emerged in dual forms, e.g., English-to-French translation vs. French-to-English translation, speech recognition vs. speech synthesis, question answering vs. question generation, and image classification vs. image generation. While structural duality is common in AI, most learning algorithms have not exploited it in learning/inference. Dual learning is a new learning framework that leverages the primal-dual structure of AI tasks to obtain effective feedback or regularization signals to enhance the learning/inference process. Dual learning has been studied in different learning settings and applied to different applications. In this tutorial, we will give an introduction to dual learning, which is composed by three parts. In the first part, we will introduce dual semi-supervised learning and show how to efficiently leverage labe...

1 mentions: @Rigeru12345
Keywords: tutorial
Date: 2019/08/10 12:54

Referring Tweets

@Rigeru12345 https://t.co/YbCkjddZvf IJCAI19のdual learningのチュートリアル(スライドDL可) 聞いてて思ったけどNLP/Image系の精度改善タスク(特に生成)はRLとかGANの知識が必須になりつつある…

Related Entries

Read more GitHub - fchollet/keras-resources: Directory of tutorials and open-source code repositories for work...
Read more MIRU2018 tutorial
Read more [KDD 2018 tutorial] End to-end goal-oriented question answering syste…
Read more GitHub - hindupuravinash/nips2016: A list of resources for all invited talks, tutorials, workshops a...
Read more KDD17 Tutorial: Learning Representations of Large-scale Networks - Jian Tang's Homepage