CityU SDSC Seminar – Promises of Machine Learning from Material Discovery to Dynamic Resource Allocation

The CityU Online Seminar named “Promises of Machine Learning from Material Discovery to Dynamic Resource Allocation” was organized by The School of Data Science (SDSC) and The Hong Kong Institute for Data Science (HKIDS) and was held on 27^th Jan 2021.  This talk invited Prof. Jay H Lee (Professor, Dept. of Chemical & Biomedical Engineering; Korea Advanced Institute of Science and Technology) as guest speaker and he would critically examine the main motivation behind and advances in deep learning. 

In the beginning, Prof. Lee briefed different branches of machine learning included unsupervised learning, supervised learning and reinforcement learning.  It also separated to passive and active learning. Machine Learning employed in the image classification & Alpha-Go that were very success.

Then Prof. Lee introduced the Machine Learning used in material science. Active Bayesian Learning to search for optimal composite composition was mentioned.

The overall approach was showed from initial experiment to property prediction and recommendation for next experiment until satisfied the objective for new material composition. So that property prediction model plus validation is important.  And then he shared some case studies including industrial composite material. 

After that Prof. Lee discussed more ambition goal to use AI inverse design for new synthesized molecule. Inverse design included high-through virtual screening (e.g. with 3 filtering stages) and optimization, evolutionary strategies, generative models (e.g. Variational Auto Encoders (VAEs), Generative adversarial networks (GAN) & Reinforcement learning (RL)). 

However, there were three problems of inverse material discovery that were Huge Chemical Space, Mapping between Chemical Space & Functional Space, as well as, Efficient Molecular Representation and Generative Model are needed.

Finally, he mentioned the next challenge was structure-property-performance for generated user-desired material (e.g. zeolites).  He also explained why reinforcement learning for dynamic resource allocation problem. It was because of “Combinatorically Complex”, “Dynamics are simple and results are easy to evaluate”, and “Significant Stochastic Uncertainties”.

Lastly, Prof. Lee concluded recent enthusiasm in machine learning is spurred by algorithmic advances in deep learning and hardware advances (e.g. GPUs).  And deep learning is particularly effective for automatic feature extraction from very high dimensional data.  At the end, he showed the Hype Cycle that ML located on the top.

Q&A

I asked about chemical reaction that were too many parameters.  Prof. Lee agreed and he added if many missing data that model would be over-fitting.

Reference:

SDSC - https://www.sdsc.cityu.edu.hk/

HKIDS - https://www.cityu.edu.hk/hkids/

Poster - https://www.cityu.edu.hk/sdsc_web/seminar/2020-09-17_sdsc_seminar.pdf

Other CityU’s AI seminar:

20201023: CityU Distinguished Seminar Series – Artificial Intelligence – Computing, Algorithm, Interaction - https://qualityalchemist.blogspot.com/2020/10/cityu-distinguished-seminar-series.html

20200917: CityU SDSC Seminar - Big Data, Deep Learning, and Federated Learning Research at Baidu - https://qualityalchemist.blogspot.com/2020/09/cityu-sdsc-seminar-big-data-deep.html

20200819: CityU Staff Seminar - Copyright As An Obstacle to AI Development - https://qualityalchemist.blogspot.com/2020/08/cityu-staff-seminar-copyright-as.html

20191101: CityU & PolyU Jointly Seminar on Attacks and Defenses on Machine Learning Services - https://qualityalchemist.blogspot.com/2019/11/cityu-polyu-jointly-seminar-on-attacks.html

20190912: CityU Seminar on the challenges and responses of AI to Public Management - https://qualityalchemist.blogspot.com/2019/09/cityu-seminar-on-challenges-and.html

20190814: CityU & NVIDIA Technology Sharing - AI Application and Research - https://qualityalchemist.blogspot.com/2019/08/cityu-nvidia-technology-sharing-ai.html

20190409: CityU & TFI Seminar – AI for Better Health and Wealth - https://qualityalchemist.blogspot.com/2019/04/cityu-tfi-seminar-ai-for-better-health.html

20190409: AI and E-Commerce: Ethical Conflicts《人工智能與電子商貿：倫理對弈》 - https://qualityalchemist.blogspot.com/2019/04/ai-and-e-commerce-ethical-conflicts.html

20190322: CityU President's Lecture series - Big Data Analysis & AI: Opportunities & Challenges - https://qualityalchemist.blogspot.com/2019/03/cityu-presidents-lecture-series-big.html

20190227: CityU Seminar on Design of Accident Prevention System for LWR using ANN and HS Simulator - https://qualityalchemist.blogspot.com/2019/02/cityu-seminar-on-design-of-accident.html

20190128: CityU Distinguished Lecture on AI Enabled Personalized Theranotics - https://qualityalchemist.blogspot.com/2019/01/cityu-distinguished-lecture-on-ai.html

20190122: CityU Seminar on The First Step for AI-based Human-Like Language Understanding – Sentiment Analysis of Text - https://qualityalchemist.blogspot.com/2019/01/cityu-seminar-on-first-step-for-ai.html

20181227: CityU Distinguished Lecture - How to Make an Artificial Vision System Smart? - https://qualityalchemist.blogspot.com/2018/12/cityu-distinguished-lecture-how-to-make.html

20181114: CityU the 1st Workshop on Financial Data Analysis - https://qualityalchemist.blogspot.com/2018/11/cityu-1st-workshop-on-financial-data.html

20180804: HKSQ AGM Quality Innovation Seminar on “Extenics and AI Application” - https://qualityalchemist.blogspot.com/2018/08/hksq-agm-quality-innovation-seminar-on.html

20180607: CityU Workshop on AI in the Era of Big Data - https://qualityalchemist.blogspot.com/2018/06/cityu-workshop-on-ai-in-era-of-big-data.html