Ordered Weighted Averaging (OWA), Decision Making Under Uncertainty, and Deep Learning: How Is This All Related?

Among many research areas to which Ron Yager contributed are decision making under uncertainty (in particular, under interval and fuzzy uncertainty) and aggregation – where he proposed, analyzed, and utilized the use of Ordered Weighted Averaging (OWA). The OWA algorithm itself provides only a specific type of data aggregation. However, it turns out that if we allows several OWA stages one after another, we get a scheme with a universal approximation property – moreover, a scheme which is perfectly equivalent to deep neural networks. In this sense, Ron Yager can be viewed as a (grand)father of deep learning. We also show that the existing schemes for decision making under uncertainty are also naturally interpretable in OWA terms.

From Goal Programming for Continuous Multi-Criteria Optimization to the Target Decision Rule for Mixed Uncertain Problems

Goal programming (GP) is applied to the discrete and continuous version of multi-criteria optimization. Recently, some essential analogies between multi-criteria decision making under certainty (M-DMC) and scenario-based one-criterion decision making under uncertainty (1-DMU) have been revealed in the literature. The aforementioned similarities allow the adjustment of GP to an entirely new domain. The aim of the paper is to create a new decision rule for mixed uncertain problems on the basis of the GP methodology. The procedure can be used by pessimists, optimists and moderate decision makers. It is designed for one-shot decisions. One of the significant advantages of the novel approach is related to the possibility to analyze neutral criteria, which are not directly taken into account in existing classical procedures developed for 1-DMU.

Soft clustering and interval type-2 fuzzy set based inference strategy for I.T. personnel selection

Impreciseness and uncertainty are the fabrics that make life interesting. For decades, human beings have developed strategies to cope with uncertainties and automate them. In personnel selection for the I.T. field, selectors often find it very difficult to select candidates by going through a set of resumes containing similar kinds of skills. Hence the selection task becomes a fuzzy decision making with the uncertainty involved. A combination of fuzzy clustering and Interval Type-2 fuzzy sets (IT2FS) is proposed in such scenarios. An experiment is conducted over a resume dataset containing fifteen hundred resumes for a particular job description. Firstly, Fuzzy C-means clustering (FCM) is applied for selective clustering, while decision-making under uncertainty is carried through IT2FS. The candidates in the selected cluster are given a score for ranking as per the skillset criteria. The final decision for shortlisting the resumes is carried through IT2FS. The model shows an average accuracy of 88.2% with an F1-score of 0.76 compared to (K-means + IT2FS) model with an F1-score of 0.72. Thus, the proposed model performs better while decision-making under uncertainty.

Decision-Making in Rats is Sensitive to Rare and Extreme Events: the Black Swan Avoidance

Most studies assessing decision-making under uncertainty use events with probabilities that are above 10-20 %. Here, to study decision-making in radical uncertainty conditions, Degoulet, Willem, Baunez, Luchini and Pintus provide a novel experimental design that aims at measuring the extent to which rats are sensitive - and how they respond - to extremely rare (below 1% of probability) but extreme events in a four-armed bandit task. Gains (sugar pellets) and losses (time-out punishments) are such that large - but rare - values materialize or not depending on the option chosen. The results show that all rats diversify their choices across options. However, most rats exhibit sensitivity to rare and extreme events despite their sparse occurrence, by combining more often options with extreme gains (Jackpots) and/or avoidance of extreme losses (Black Swans). In general, most rats choices feature one-sided sensitivity in favor of trying more often to avoid extreme losses than to seek extreme gains - that is, they feature Black Swan Avoidance.