The 5th Deep Learning and Artificial Intelligence Summer School 2021 (DLAI5)
APNNS/IEEE-CIS Education Forum Series
The APNNS/IEEE-CIS Education Forum series on Deep Learning and Artificial Intelligence Summer School 2020 (DLAI5) is catered to all interested students, engineers, researchers, executives and administrators who may have some basic knowledge of machine learning and AI. The aim is to provide a forum for interested delegates to learn about certain basics as well as advances in the field of deep learning and artificial intelligence. DLAI5 would also provide an opportunity for interactions and networking. With the successful inaugural DLAI back on Feb 1-4, 2018, the second edition on Dec 10-13, 2018, the third edition on June 29 to July 3, and the latest DLAI4 on November 18-22, 2020, we are pleased to be able to offer the 5th DLAI at this time. The venue is online due to the ongoing pandemic and it will be held from May 6-10, 2021. DLAI5 will feature Keynote and Invited Speakers from IEEE Distinguished Lecturers, ACM Distinguished Speakers, and other notable speakers. In addition to Women in Science and Engineering (WISE) speakers, DLAI5 is proud to introduce the Forum for Young Investigators (FYI) as there will be prominent young researchers sharing their experiences with us.
As DLAI5 is a virtual event, it is offered free-of-charge to all registrants. All participants need to register online first. As there may be limited seating available as an online event, priorities will be given to APNNS Members, IEEE-CIS Members, IEEE Members, ACM Members, and INNS Members.
The DLAI5 Summer School will cover many aspects of deep learning with several talks by world renowned researchers in form of lectures/tutorials/workshops and panel sessions which will cover some of the most active current topics in DL and AI and their applications. There are two NVIDIA Deep Learning Institute (DLI) certification workshops, and a hackathon will also be offered to provide a hands-on challenge for the participants.
DLAI5 is organized by the Innovative Cognitive Computing (IC2) Research Center at School of Information Technology (SIT), King Mongkut's University of Technology Thonburi (KMUTT) and co-organized by APNNS, IEEE-CIS Thailand Chapter, Joint Chapter of IEEE CIS/RAS Western Australia Chapter, IEEE-SMC Western Australia Chapter, IEEE-CIS Indonesia Chapter, and various partner institutions, with the latest being the Technology Innovation Hub at Indian Statistical Institue (TIH@ISI) and Jadavpur University, India.
Date and Time
- Start time: 06 May 2021 08:00 AM
- End time: 10 May 2021 05:00 PM
- All times are (GMT-07:00) Etc/GMT+7
- Add Event to Calendar
- Contact Event Hosts
- Co-sponsored by ACM, NVIDIA, Forth, 3BB, Cinmit
Pau-Choo (Julia) Chung of National Cheng Kung University
Gait and Balance Analysis for the Elderly Using an Inertial-Sensor-Based Wearable Device
Gait and balance patterns are two major measurements for the evaluation of the elderly’s physical conditions and are therefore often used in the early detection of certain diseases. For example, patients with Alzheimer’s disease (AD) were reported of revealing gait disorders and balance problems. In this talk we will present an inertial-sensor based wearable device, which are designed for objective quantitative measurement of gait patterns and balance capabilities. Accompanied with the device are the algorithms and CI models, which integrally provide the quantitative evaluations. We will also discuss several essential indicators from gait and balance patterns for AD
diagnosis. The gait analyzing algorithm, which is composed of stride detection followed by gait cycle decomposition, and the balance analysis algorithm, which is measured by the sway speed in anterior-posterior (AP) and medial-lateral (ML) directions of the
projection path of body’s center of mass (COM), will also be introduced.
Pau-Choo (Julia) Chung (S’89-M’91-SM’02-F’08) received the Ph.D. degree in electrical engineering from Texas Tech University, USA, in 1991. She then joined the Department of Electrical Engineering, National Cheng Kung University (NCKU), Taiwan, in 1991 and has become a full professor in 1996. She served as the Director of Institute of Computer and Communication Engineering (2008-2011), the Vice Dean of College of Electrical Engineering and Computer Science (2011), the Director of the Center for Research of E-life Digital Technology (2005-2008), and the Director of Electrical Laboratory (2005-2008), NCKU. She was elected Distinguished Professor of NCKU in 2005. She also
served as Chair of Department of Electrical Engineering, NCKU.
Dr. Chung’s research interests include image/video analysis and pattern recognition, biosignal analysis, computer vision and computational intelligence. She applies most of her research results to healthcare and medical applications. Dr. Chung served as the program committee member in many international conferences. She was a Member on IEEE International Steering Committee, IEEE Asian Pacific Conference on Circuits and Systems (2006-2008), the Special Session Co-Chair of ISCAS 2009 and 2010, the Special Session Co-Chair of ICECS 2010, and the TPC of APCCAS 2010. Dr. Chung was the Chair of IEEE Computational Intelligence Society (CIS) (2004-2005), Tainan Chapter. She was the Chair of the IEEE Life Science Systems and Applications Technical Committee (2008-2009) and a member of the BioCAS Technical Committee
and the Multimedia Systems & Applications Technical Committee of the CAS Society. She also serves as the Associate Editor of IEEE Transactions on Neural Networks and served as the Editor of Journal of Information Science and Engineering, the Guest Editor of Journal of High Speed Network, the Guest Editor of IEEE Transactions on Circuits and Systems-I, and the Secretary General of Biomedical Engineering Society of the Republic of China. She is one of the co-founders of Medical Image Standard Association (MISA) in Taiwan and served on the Board of Directors of MISA.
Pau-Choo Chung was a member in BoG of CAS Society (2007-2009, 2010-2012). She served as an IEEE CAS Society Distinguished Lecturer (2005-2007). She is an ADCOM member of IEEE CIS and current Vice President for Education. She is a Member of Phi
Tau Phi honor society and is an IEEE Fellow since 2008.
Saman Halgamuge of The University of Melbourne
Democratisation of Deep Learning: Self Growing Neural Network Architectures
In the past decade, Deep Neural Networks (DNNs) based on supervised learning have revolutionized various fields including Computer Vision, Natural Language Processing, Bioinformatics and Robotics. Behind this revolution is the increasing demand for computational power, with reportedly the amount of computing used in the training of largest manually designed DNN models doubling every 3.5 months since 2012, much faster than the two-year doubling period of Moore’s law in electronic hardware advancement. While continually meeting such a demand is unsustainable and unlikely, a need arises for significant innovations in discovering or designing DNN architectures and training procedures that are significantly more efficient and demand much less computing power, i.e., low cost. Such innovations could also benefit the wider use of DNNs by researchers without expertise in DNN design in many new areas including in energy, environmental and social sciences and arts and humanities.
To reduce the development cost of DNNs, a recent idea proposed is to automate the DNN design, which leads to an emerging field called automatic machine learning (Auto-ML). However, this idea was previously applied by the author on shallow Neural Networks using Self generation/growing [1-3]. Existing Auto-ML methods have attempted to optimize every step of the data analysis pipeline including data
preparation, feature engineering, model generation, training, and evaluation. Among them, Neural Architecture Search (NAS) methods explicitly find DNN architectures for a given supervised learning task. This is achieved by encoding the candidate architecture as a solution in some search space and treating the architecture design as an optimization problem. Growing Neural Network Architectures instead of “searching for the best” has been our strategy to this problem.
Our research shows that Self Growing Neural Networks can be used both in Unsupervised Learning and Supervised Learning. In the former, they can be applied to continuous data streams. In the latter, our techniques also lead to interpretable architectures. We also refer to recent work jointly published with Dr Damith Senanayake, Dr Wei Wang and others [3-6].
Acknowledgment: This research is funded by ARC Discovery project grant DP210101135.
1. SK Halgamuge, M Glesner, “Neural Networks in Designing Fuzzy Systems for Real World Applications”, Fuzzy Sets and Systems 65 (1), 1-12, 1994
2. SK Halgamuge, W Pochmueller, M. Glesner, “An Alternative Approach for Generation of Membership Functions and Fuzzy Rules Based on Radial and Cubic Basis Function Networks”, International Journal of Approximate Reasoning 12 (3), 4, 1995
3. SK Halgamuge, “Self Evolving Neural Networks for rule based data processing”, IEEE Transactions on Signal Processing, 45 (11), 2766-2773, 1997
4. D Senanayake, W Wang, SH Naik, S Halgamuge, “Self Organizing Nebulous Growths for Robust and Incremental Data Visualization”,
IEEE Transactions on Neural Networks and Learning Systems, 2020
5. W Wang, Y Sun, S Halgamuge, “Improving MMD-GAN Training with Repulsive Loss Function”, International Conference on Learning Representations (ICLR 2019), 2019
6. PN Hameed, K Verspoor, S Kusljic, S Halgamuge, “Positive-unlabeled learning for inferring drug interactions based on heterogeneous attributes”, BMC bioinformatics 18 (1), 1-15, 2017.
Prof Saman Halgamuge is a Fellow of IEEE, a Professor in the School of Electrical, Mechanical and Infrastructure Engineering and a Distinguished Speaker/Lecturer on Computational Intelligence (2019-2021). He served as Director/Head, Research School of Engineering of the Australian National University (ANU) (2016-18), a member of Australian Research Council (ARC) College of Experts for Engineering, Information and Computing Sciences (2016-18), the founding Director of the PhD training centre Melbourne India Postgraduate Program (MIPP) of University of Melbourne and Associate Dean (2013-15) and Assistant Dean (2008-13) in International Engagement in the Melbourne School of Engineering. Saman is also an honorary Professor of ANU.
Day1: Thursday, May 6, 2021
DLAI5 Opening Remarks 7.50-8 Welcome speech
Academic Keynote I 8-9 Kenji Doya-What can we further learn from the brain for AI?
ACM Distinguished Speaker 9-10 Ka-Chun Wong-Disruptive AI Technologies for Molecular Biology and Medicine
NVIDIA DLI Workshop I (Part I) 10.15-12.30 Jonathan H. Chan Fundamentals of Deep Learning
Panel Session I 13-14.30 Chrisina Jayne, Yew-Soon Ong, Weizhi Meng-Explainable and Ethical AI
ACM Distinguished Speaker II 14.30-15.30 Weizhi Meng-Securing Smart Devices with Behavioral User Authentication
NVIDIA DLI Workshop I (Part II) 15.30-17 Jonathan H. Chan-Fundamentals of Deep Learning
Day2: Friday, May 7, 2021
Academic Keynote II 8-9 Albert Zomaya-Lightweight Short-term Photovoltaic Power Prediction for Edge Computing
Academic Talk 9-10 Vishnu Bodetti-Towards Learning Semantically Controllable Representations
NVIDIA DLI Workshop II (Part I) 10-12.30 Jonathan H. Chan-Deep Learning for Healthcare Image Analysis
Academic Talk 12-14 Chee Seng Chan-DeepIPR-Protecting Intellectual Property of Deep Learning Models
NVIDIA DLI Workshop II (Part II) 14-15.30 Jonathan H. Chan-Deep Learning for Healthcare Image Analysis
Hackathon Session I 15.30-17 Paul Pang-CDMC2021-Towards Secure, Explainable and Trustworthy Artificial Intelligence + Jonathan H. Chan-Hackathon
Day3: Saturday, May 8, 2021
WISE Keynote 8-9 Deepa Kundur-Analytics-Driven Cyber-Physical Security for a Converged Smart Grid
IEEE-CIS Distinguished Lecturer Talk I 9-10 Pau-Choo (Julia) Chung-Gait and Balance Analysis for the Elderly Using an Inertial-Sensor-Based Wearable Device
WISE Industry Talk 10-11 Yingxue Zhang-Bayesian Graph Neural Networks and its application in recommendation system
WISE Academic Talk 11-12 Claire Chewapreecha-Dissecting the genetic basis of Melioidosis Infection
FYI Academic Talk 13-14 Haiqin Yang-Towards building emphathetic chatbots
FYI Industry Talk 14-15 Tanut Karnwai-Imbalanced credit card fraud detection via using deep neural network
FYI Academic Talk 15-16 Wittawat Jitkrittum-Interpretable Comparison of Deep Generative Models
Day4: Sunday, May 9, 2021
IEEE-CIS Distinguished Lecturer Talk II 8-9 Saman Halgamuge-Democratisation of Deep Learning: Self Growing Neural Network Architectures
FYI Academic Talk 9-10 Worrawat Engchuan-Deep learning in genetic study of ASD
FYI Academic Talk 10-11 Rajarshi Pal-AI for handwritten document forensic
WISE Academic Talk 13-14 Guanjin (Brenda) Wang-Solving real-world data challenges using machine learning
WISE Academic Talk 14-15 Sansanee Auephanwiriyakul-Fuzzy Pattern Recognition in Data Analysis
WISE Academic Talk 15-16 Shirley Siu-Targeted Anticancer Peptides Discovery: Machine Learning and Molecular Study
WISE Academic Talk 16-17 Annalisa Occhipinti-Healthcare and AI: Promising Applications for Cancer Prediction
Day5: Monday, May 10, 2021
JSCI10 Keynote I 8-9 Sung-Bae Cho-Exploiting Latent Space of Deep Learning for Practical Applications
Panel Session II 9-10.15 Sung-Bae Cho, Ashish Ghosh, Jonathan Chan-AI for COVID-19
JSCI10 Industry Talk 10.15-11 Monchai Lertsutthiwong-Global challenge for AI in business transformation
JSCI10 Keynote II 13-14 Claudio Angione-Deep learning approaches to predict the cell metabolic phenotype
JSCI10 Student Session 14-15.30
Hackathon+Wrap up 15.45-17