Time	Contents	Host
13:00--13:15	Welcoming and introduction ， VP, Professor Mingyi He	Mingyi He
	Opening Words from President, Prof Tatsuya Kawahara
13:15--14:00	Part 1, Overview of Neural Network AI [by Mingyi He]	Yuanman LI
	1.1.      From Nobel Prize Physics 2024 to the theme
	1.2.      Advance of Artificial Neural Networks
	1.3.      Typical Neural Networks/Machine Learning: MLP, HNN, RNN, DCNN, Skip- connection NN, Transformer, GPT, etc) for SIP
	1.4.      The challenges on NN AI
	1.5.      Question and answer
14:00-15:00	Part 2, Hopfield Neural Network Foundation for Machine Learning [by Mingyi He]	Yuanman LI
	2.1.      Hopfield neural network (HNN) -Circuit model and analysis
	2.2.      Lyapunov function and dynamic system stability
	2.3.      Hopfield energy function and HNN stability
	2.4.      HNN for pattern recognition and optimization applications
	2.5.      Bolzmann machine for feature learning and generative models
	2.6.      Modern HNN in deep learning
	2.7.      Hopfield Lyapunov function for TSP and New Lyapunov function for TBP
	2.8.      Question and answer
	Break
15:30--16:30	3.1.      Part 3, Deep Learning for Image forensics [by Bonnie Law]	Yuan Wu
	3.2.      Introduction to Image forensics
	3.3.      Typical neural models for image forensics
	3.4.      Deep learning models for image forensics (source identification and forgery detection)
	3.5.      Advanced applications for DL (e.g., image tampering localization and open-set source identification)
	3.6.      Challenges
	3.7.      Discussion
16:30--17:30	4.1.      Part 4, Generative Modeling and Learning for Conversational AI  [by Jen-Tzung Chien ]	Yuan Wu
	4.2.      Background of spoken dialogue systems
	4.3.      Multimodal machine learning
	4.4.      Multilingual generative models
	4.5.      Pre-trained foundation models
	4.6.      Challenges and opportunities in comprehensive conversation system.
	4.7.      Discussion
17:30--17:50	Overview and Discussions	All
	Closing words from New VP, Prof Isao Echizen