Scope and Aim
The special session is aimed to update the research community with the current challenges, recent progress, and future outlook related to robustness and trustworthiness issues in deep learning. The estimation of uncertainty or confidence in the predictive decisions is an integral part of a robust and trustworthy autonomous system — potential examples include medical diagnosis, security systems, self-driving, financial decision-making, and smart and connected cities. Currently, adversarial examples, i.e., inputs to machine learning models designed to cause the model to make a mistake, are limiting the wide-spread use of these models in real-world applications. Bayesian techniques may provide one way to introduce uncertainties in learning systems by defining probability distributions over unknown parameters and make these models robust to adversarial attacks. This special session will focus on uncertainty estimation, robustness, and trustworthiness techniques as applied to modern learning.
Topics Covered
The aim of the special session on "Robustness and Trustworthiness in Deep Learning" is to provide a forum for engineers, scientists, and researchers of this field to exchange the latest advances in theories and experiments. Researchers are invited to submit original and unpublished theoretical and experimental results in the following and related areas.
Submission Guidelines:
This special session will be held in 2020 International Joint Conference on Neural Networks-IJCNN (wcci2020.org/ijcnn-sessions/), a part of 2020 IEEE World Congress on Computational Intelligence (https://wcci2020.org/ ) (Glasgow, Scotland, United Kingdom, July 19-24, 2020). All papers should be prepared according to the IJCNN 2020 policy and should be submitted electronically using the conference website (https://wcci2020.org/ ) . To submit your paper to this special session, you will choose our special session on the submission page "Robustness and Trustworthiness in Deep Learning". All papers accepted and presented at IEEE IJCNN/WCCI 2020 will be included in the conference proceedings published by IEEE Explore, which are typically indexed by EI.
Organizers:
Dr. Ghulam Rasool received his Ph.D. in Systems Engineering from the University of Arkansas at Little Rock in 2014 and MS in Computer Engineering from Center for Advanced Studies in Engineering (CASE), Pakistan, in 2010. He was a postdoctoral fellow at Northwestern University from 2014 to 2016, working in the areas of machine learning, biomedical image/signal processing, and control systems. He is currently an Assistant Professor of Electrical and Computer Engineering at the Henry M. Rowan College of Engineering of Rowan University. His recent work on Bayesian machine learning and uncertainty estimation titled “Extended Variational Inference for Propagating Uncertainty in Convolutional Neural Networks” won the Best Student Award (first position) at the IEEE MLSP 2019. He is the PI of the US Department of Education’s $1.2M GAANN award titled “Rowan’s Graduate Fellowship Prepares for the Modern Age of Artificial Intelligence (Rowan’s Prepare.AI.” He has been receiving research support from the US National Science Foundation (NSF), New Jersey Department of Transportation (NJDOT), New Jersey Health Foundation (NHF), the Federal Aviation Administration (FAA), Google, and NVIDIA. His research interests include machine intelligence, robust learning, reinforcement learning, and control systems.
Dr. Nidhal C. Bouaynaya received the B.S. degree in Electrical and Computer Engineering from the National School of Electrical Engineering, Computer Science and Telecommunications (ENSEA), France, in 2002 along with the M.S. degree in Electrical and Computer Engineering from the Illinois Institute of Technology, Chicago, IL, in 2002, the M.S. diploma (DEA) in Signal and Image Processing from ENSEA, France, in 2003, the M.S. degree in Mathematics and the Ph.D. degree in Electrical and Computer Engineering from the University of Illinois at Chicago, Chicago, IL, in 2007. She is currently a Professor and Associate Dean of Research and Graduate Studies with the Henry M. Rowan College of Engineering. Her research interests are in signal processing, machine learning, big data analytics and optimization. Dr. Bouaynaya won numerous Best Paper Awards (IEEE MLSP 2019, IEEE BIBM 2015, IEEE GENSIPS 2013, SPIE VCIP 2006, SPIE IVCP 2005) and Top algorithm at the 2016 Multinomial Brain Tumor Segmentation Challenge. Her research is funded by the US National Science Foundation (NSF), The US National Institutes of Health (NIH), New Jersey Department of Transportation (NJ DoT), US. Department of Agriculture (USDA), the Federal Aviation Administration (FAA) and Lockheed Martin. She is also interested in entrepreneurial endeavors. In 2017, she Co-founded and is Chief Technology Officer (CTO) of MRIMATH, LLC, a start-up company in medical imaging.
Dr. Lyudmila Mihaylova, MSc, PhD is a Professor of Signal Processing and Control in the Department of Automatic Control and Systems Engineering at the University of Sheffield, Sheffield, United Kingdom. Her research interests are in the areas of autonomous systems with applications to cities, autonomous and assisted living systems. She has expertise in the areas of machine learning, intelligent sensing and sensor data fusion. She won the Tammy Blair best award from the International Conference of Information Fusion 2017, best student paper awards from the IEEE DESSERT’2019, 17th IEEE SPA’2013 Conference and IEEE Sensor Data Fusion Workshop, 2013. Prof. Mihaylova is on the Board of Directors of the International Society of Information Fusion (ISIF) and was the ISIF President in the period 2016–2018. She has given a number of talks and tutorials, including NATO SET- 262 AI 2018 (Hungary), Fusion 2017 (Xi’an, China), plenary talks for the IEEE Sensor Data Fusion 2015 (Germany), invited talks at IPAMI Traffic Workshop 2016 (USA) and others. She was the general vice-chair for the International Conference on Information Fusion 2018 (Cambridge, UK), of the IET Data Fusion & Target Tracking 2014 and 2012 Conferences, publications chair for ICASSP 2019 (Brighton, UK) and others.
Dr. Peng Wang is working as a research associate with the Department of Automatic Control and Systems Engineering. He is dedicated to providing reliable solutions to the Internet of Things (IoT) era. His research focuses on: machine learning methods in image and traffic data processing, with a specific interest in quantifying the uncertainty of the deep learning by using Gaussian processes; autonomous vehicle/robot localization/SLAM with LiDAR, computer vision, and GPS, etc., with the purpose of developing trustworthy methods; IoT driven solutions for advancing traditional manufacturing industry, for the sake of sustainable development. His Sheffield based funding awards include Co-I to a knowledge exchange project “Internet of Things for overcoming barriers in the steel rolling measurement technology”.