知能情報論 - 情報理工学系研究科 - 東京大学授業カタログ

知能情報論

知能情報論／ Intelligent Informatics

知能の根元には情報を介した主体と環境とのインタラクションがあり，人間を含めた実環境からの情報をいかに要約し利用するかが知能システム構築のカギとなる．ここでは，その基礎理論，知能システムの原理や仕組み，さらに具体的な応用について論じる．
／
An interaction between agent and environment via information is a base of intelligence. Therefore how to summarize and utilize information from the real environment is a key element in building intelligent systems. This class will introduce you to a basic theory of intelligent information processing and give you experience creating an object recognition system from images.

MIMA Search

授業計画

4/9: Introduction: What are image understanding and generation? (Tatsuya Harada, UTokyo) 4/16: Fundamentals of Deep Learning 1 (Recognition, FFNN, CNN, RNN, Transformer, etc.) (Tatsuya Harada, UTokyo) 4/23cancel 4/30: Fundamentals of Deep Learning 2 (Generation: VAE, GAN, Flow Matching, Diffusion Models, etc.) (Tatsuya Harada, UTokyo) 5/14: Fundamental Tasks in Image Recognition (classification, detection, segmentation, etc.) (Tatsuya Harada, UTokyo) 5/21: Representation Learning, Foundation Models, Learning from Limited Data 1 (Thomas Westfechtel / Dexuan Zhang, UTokyo) 5/28: Image Generation (Takuhiro Kaneko, NTT) 6/4: Representation Learning, Foundation Models, Learning from Limited Data 2 (Thomas Westfechtel / Dexuan Zhang, UTokyo) 6/11: Vision and Language (Kohei Uehara, SBI) 6/18: Low-Level Vision (Ziteng Cui, UTokyo) 6/25: 3D Reconstruction and Generation (Atsuhiro Noguchi, PFN) 7/2: Foundations of 3D Point Cloud Understanding: Representations, Geometry, and Core Architectures (Qianyu Zhou, UTokyo) 7/9: Scene Understanding, LiDAR, and Modern Trends (e.g., VLA and WAM) in 3D Recognition (Haozhi Cao, UTokyo)