Meet: Jerry Mendel, IEEE Lotfi A. Zadeh Pioneer Award 2021
Jerry Mendel, a long-time member of the CIS, has received the IEEE Lotfi A. Zadeh Pioneer Award – maintained by the IEEE Systems, Man, and Cybernetics Society – for developing and promoting Type-2 fuzzy logic. The IEEE Lotfi A. Zadeh Pioneer Award honors a person or persons with outstanding and pioneering contributions to academic and/or industrial research in systems science and engineering, human-machine systems, and/or cybernetics (established in 2014), made at least 15 years prior to the award date. Past awardees are: 2017—Lotfi Zadeh (honorary) and Michio Sugeno, and 2018—Ronald Yager.
What is your title, and place of work? (or Technical Field of Research)?
I am an Emeritus Professor of Electrical Engineering, Viterbi School of Engineering
University of Southern California
Although retired since 2018, I continue to research fuzzy sets and systems (mainly type-2) either individually or with colleagues from around the World.
I was a member of Fuzzy Systems TC from 2001–2015, and its Chair from 2003 –2007.
AdCom Member from 2004–2009 and 2011–2013, Chairman of Task Force on Computing With Words for the Fuzzy Systems TC from 2008-2010, AE of IEEE Trans. on Fuzzy Systems from 1994–1995 and 1999–2016.
How long have you been a member of CIS and what was the reason you chose to join IEEE CIS?
I have been a member of CIS from its inception. I joined because it covered my technical interests.
What Computational Intelligence society committee do you serve?
In the past, I used to be in many committees in CIS.
Presently, I am a member of the Continuing Education Sub-Committee and the Industrial Activities Committee (before I began my academic career I worked in industry for 11 years).
What have you learned from your experience and how has it helped you professionally?
I have been active in IEEE Societies for my entire career. Prior to my joining CIS I had been President of the IEEE Control Systems Society and EIC of the IEEE Transactions on Automatic Control. Working with the leaders and luminaries of a field has been a very rewarding experience. Being the Chair of a TC or a TF has provided me with opportunities to influence some research directions. I have also been able to make some connections with colleagues who then work with me jointly on research projects that are of mutual interest.
What has been the most fun/rewarding thing about being a volunteer for the IEEE Computational Intelligence Society? What have you enjoyed the most?
Meeting and interacting with so many interesting people.
I was asked to chair a sub-committee for creating a competition for a video that would explain what a fuzzy set is, with monetary awards to the winners. Something like this had not been done before in the CIS, and I really like doing something that no one has done before. You can let your creative juices flow. This gave me an opportunity to work with some very talented younger members of the CIS. It was an amazingly fun project, and there are now two winning You-Tube videos: “An Egg-Boiling Fuzzy Logic Robot” and “Fuzzy Logic: An Introduction.”
I have also enjoyed going to dinners with CIS colleagues after adCom meetings.
Tell us something about you that we don’t know.
I am an avid Bridge player, and have been playing for close to 60 years.
Hi all, 
Previous work has shown that adversarial learning can be used for unsupervised monocular depth and visual odometry (VO) estimation, in which the adversarial loss and the geometric image reconstruction loss are utilized as the mainly supervisory signals to train the whole unsupervised framework. However, the performance of the adversarial framework and image reconstruction is usually limited by occlusions and the visual field changes between the frames. This article proposes a masked generative adversarial network (GAN) for unsupervised monocular depth and ego-motion estimations. The MaskNet and Boolean mask scheme are designed in this framework to eliminate the effects of occlusions and impacts of visual field changes on the reconstruction loss and adversarial loss, respectively.
A smart grid ecosystem requires intelligent Home Energy Management Systems (HEMSs) that allow the adequate monitoring and control of appliance-level energy consumption in a given household. They should be able to: i) profile highly non-stationary and non-linear measurements and ii) conduct correlations of such measurements with diverse inputs (e.g. environmental factors) in order to improve the end-user experience, as well as to aid the overall demand-response optimisation process. However, traditional approaches in HEMS lack the ability to capture diverse variations in appliance-level energy consumption due to unpredictable human behavior and also require high computation to process large datasets. In this article, we go beyond current profiling schemes by proposing Deep COLA; a novel Deep COmpetitive Learning Algorithm that addresses the limitations of existing work in terms of high dimensional data and enables more efficient and accurate clustering of appliance-level energy consumption. The proposed approach reduces human intervention by automatically selecting load profiles and models variations and uncertainty in human behavior during appliance usage. 
This article is about explainable artificial intelligence (XAI) for rule-based fuzzy systems [that can be expressed generically, as y(x)=f(x). It explains why it is not valid to explain the output of Mamdani or Takagi–Sugeno–Kang rule-based fuzzy systems using IF-THEN rules, and why it is valid to explain the output of such rule-based fuzzy systems as an association of the compound antecedents of a small subset of the original larger set of rules, using a phrase such as “these linguistic antecedents are symptomatic of this output.” Importantly, it provides a novel multi-step approach to obtain such a small subset of rules for three kinds of fuzzy systems, and illustrates it by means of a very comprehensive example. 
Convolutional neural networks hold state-of-the-art results for image classification, and many neural architecture search algorithms have been proposed to discover high performance convolutional neural networks. However, the use of neural architecture search for the discovery of skip-connection structures, an important element in modern convolutional neural networks, is limited within the literature. Furthermore, while many neural architecture search algorithms utilize performance estimation techniques to reduce computation time, empirical evaluations of these performance estimation techniques remain limited. This work focuses on utilizing evolutionary neural architecture search to examine the search space of networks, which follow a fundamental DenseNet structure, but have no fixed skip connections. In particular, a genetic algorithm is designed, which searches the space consisting of all networks between a standard feedforward network and the corresponding DenseNet.
In sequential decision making, heuristic search algorithms allow exploiting both the initial situation and an admissible heuristic to efficiently search for an optimal solution, often for planning purposes. Such algorithms exist for problems with uncertain dynamics, partial observability, multiple criteria, or multiple collaborating agents. In this article, we look at two-player zero-sum stochastic games (zsSGs) with a discounted criterion, in a view to propose a solution tailored to the fully observable case, while solutions have been proposed for particular, though still more general, partially observable cases. This setting induces reasoning on both a lower and an upper bound of the value function, which leads us to proposing zsSG-HSVI, an algorithm based on heuristic search value iteration (HSVI), and which thus relies on generating trajectories. We demonstrate that, each player acting optimistically, and employing simple heuristic initializations, HSVI's convergence in finite time to an ∈-optimal solution is preserved.
