Sorry, this entry is only available in Japanese<\/a>. For the sake of viewer convenience, the content is shown below in the alternative language. You may click the link to switch the active language.<\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div> The emergence of Deep Learning technology has dramatically improved AI technology, and had a big impact on diverse industry and social institution. In the near future, every industry and its types should be influenced by AI technology. Frontier artificial intelligence II provides a project-style lecture intended acquisition of more practical ability of research and development for the learners who have a basic understanding of Deep Learning and can construct the models. Based on the idea \u201cPractice makes perfect\u201d, we aim to let you acquire the technique through the exercise. In exercise, you can concentrate on the point of the lecture by using our specific development platform \u201cilect.net\u201d <\/a>: enables you to code in Python with GPU on a browser\uff08The detail of iLect is here<\/a>\uff09.<\/p>\n application \uff08The contents are being adjusted, may be changed.)<\/p>\n <\/p>\nFrontier Artificial Intelligence II 2017\uff08The course of Graduate School of The University of Tokyo\uff09<\/h2>\n
\n
\nQ & A<\/a><\/p>\n<\/div><\/div><\/div><\/div><\/div><\/div>Program syllabus<\/h2>\n
\n\n
\n \n<\/th>\n date<\/th>\n title<\/th>\n contents<\/th>\n<\/tr>\n<\/thead>\n \n 1.<\/td>\n 2017\/09\/26<\/td>\n Introduction\/Guidance<\/td>\n – Summarization of the spring lecture
\n– Introduction of the autumn lecture, this year’s highlights, assessment of achievement, etc…<\/td>\n<\/tr>\n\n 2.<\/td>\n 2017\/10\/03<\/td>\n Advanced image recognition\uff11<\/td>\n Object recognition, CNN,\u00a0 Transfer Learning, Fine-Tuning, Introduction of open source softwares, Reuse of pre-trained network,<\/td>\n<\/tr>\n \n 3.<\/td>\n 2017\/10\/10<\/td>\n Reinforcement\uff11<\/td>\n Outline of reinforcement learning
\n– problem establishment in reinforcement learning
\n– value function based approach and policy based approach
\n– Introduction of Chainer, ChainerRL<\/td>\n<\/tr>\n\n 4.<\/td>\n 2017\/10\/17<\/td>\n Generative models\uff11<\/td>\n Outline of generative models, RBM<\/td>\n<\/tr>\n \n 5.<\/td>\n 2017\/10\/24<\/td>\n Big data and Deep Learning<\/td>\n HPC, GPU, Profilers, Database and Deep Learning<\/td>\n<\/tr>\n \n 6.<\/td>\n 2017\/10\/31<\/td>\n Team development\uff08methodology, teaming\uff09<\/td>\n Team development, Git and workflow, the project, precautions, etc…<\/td>\n<\/tr>\n \n 7.<\/td>\n 2017\/11\/07<\/td>\n Advanced image recognition\uff12<\/td>\n Region proposal, Fast\/Faster RCNN, RPN, Single-shot architecture<\/td>\n<\/tr>\n \n <\/td>\n \u203b2017\/11\/14<\/td>\n \uff08no lectures\uff09<\/td>\n<\/tr>\n \n 8.<\/td>\n 2017\/11\/21<\/td>\n Reinforcement learning\uff12<\/td>\n Value function based approach
\n– DQN and respective researches
\n– Expansion of continuous actions<\/td>\n<\/tr>\n\n 9.<\/td>\n 2017\/11\/28<\/td>\n Generative models\uff12<\/td>\n \u00a0Variational Auto Encoder (VAE) and respective topics<\/td>\n<\/tr>\n \n 10.<\/td>\n 2017\/12\/05<\/td>\n Advanced image recognition\uff13<\/td>\n \u00a0Segmentation<\/td>\n<\/tr>\n \n 11.<\/td>\n 2017\/12\/12<\/td>\n Generative models\uff13<\/td>\n Generative Adversarial Networks (GAN) and respective topics<\/td>\n<\/tr>\n \n 12.<\/td>\n 2017\/12\/19<\/td>\n Reinforcement learning\uff13<\/td>\n Policy based approach
\n– Policy gradient
\n– A3C, TRPO, PPO
\n– Case studies (Acrobot, Atari, etc…)<\/td>\n<\/tr>\n\n 13.<\/td>\n 2018\/1\/9<\/td>\n Interim report<\/td>\n Lightning talk style<\/td>\n<\/tr>\n \n <\/td>\n 2018\/1\/16<\/td>\n a supplementary class<\/td>\n <\/td>\n<\/tr>\n \n <\/td>\n 2018\/1\/20<\/td>\n “Final report \uff08Deep Learning Day\uff09<\/a><\/td>\n Keynote address, presentation, poster and demo session<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/p>","protected":false},"excerpt":{"rendered":"","protected":false},"author":3,"featured_media":0,"parent":552,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_acf_changed":false,"footnotes":""},"tags":[],"class_list":["post-7042","page","type-page","status-publish","hentry"],"acf":[],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\t\n\n\t\t\n