I am regularly asked to summarize my many posts. I thought it would be a good idea to publish on this blog, every Monday, some of the most relevant articles that I have already shared with you on my social networks. Today I will share some of the most relevant articles about Artificial Intelligence and in what form you can find it in today's life. I will also comment on the articles. Artificial Intelligence is often viewed as a potential threat to humanity, but it can also be viewed as a valuable tool. From self-driving cars to automated security systems, AI is gradually becoming a valuable resource in our everyday lives.

Western Connecticut State University Department of Philosophy and Humanistic Studies will present Dr. Rick Lawrence, of Ridgefield, for a discussion, "COVID-19: Perspectives from a Data Scientist," at 5:30 p.m. on Wednesday, Nov. 3, in Room 125 of the Science Building on the university's Midtown campus, 181 White St., Danbury. The talk is free and open to the public in-person (masks must be worn) or virtually through this link. The program is also sponsored by WCSU's Department of Computer Science and Department of Mathematics. Lawrence currently volunteers as the COVID data scientist on Ridgefield's COVID-19 Task Force, providing daily analysis of the latest COVID-19 data to help town officials make science-based policy decisions, and provides periodic analysis of vaccination rates to the Office of the Governor of Connecticut. Lawrence's work has evolved from nuclear science to computer science to machine learning and, most recently, to quantitative finance.

Critical evaluation and understanding of ship responses in the ocean is important for not only the design and engineering of future platforms but also the operation and safety of those that are currently deployed. Simulations or experiments are typically performed in nominal sea conditions during ship design or prior to deployment and the results may not be reflective of the instantaneous state of the vessel and the ocean environment while deployed. Short-term temporal predictions of ship responses given the current wave environment and ship state would enable enhanced decision-making onboard for both manned and unmanned vessels. However, the current state-of-the-art in numerical hydrodynamic simulation tools are too computationally expensive to be employed for real-time ship motion forecasting and the computationally efficient tools are too low fidelity to provide accurate responses. A methodology is developed with long short-term memory (LSTM) neural networks to represent the motions of a free running David Taylor Model Basin (DTMB) 5415 destroyer operating at 20 knots in Sea State 7 stern-quartering irregular seas. Case studies are performed for both course-keeping and turning circle scenarios. An estimate of the vessel's encounter frame is made with the trajectories observed in the training dataset. Wave elevation time histories are given by artificial wave probes that travel with the estimated encounter frame and serve as input into the neural network, while the output is the 6-DOF temporal ship motion response. Overall, the neural network is able to predict the temporal response of the ship due to unseen waves accurately, which makes this methodology suitable for system identification and real-time ship motion forecasting. The methodology, the dependence of model accuracy on wave probe and training data quantity and the estimated encounter frame are all detailed.

In the analysis of data sets consisting of (X, Y)-pairs, a tacit assumption is that each pair corresponds to the same observation unit. If, however, such pairs are obtained via record linkage of two files, this assumption can be violated as a result of mismatch error rooting, for example, in the lack of reliable identifiers in the two files. Recently, there has been a surge of interest in this setting under the term "Shuffled data" in which the underlying correct pairing of (X, Y)-pairs is represented via an unknown index permutation. Explicit modeling of the permutation tends to be associated with substantial overfitting, prompting the need for suitable methods of regularization. In this paper, we propose a flexible exponential family prior on the permutation group for this purpose that can be used to integrate various structures such as sparse and locally constrained shuffling. This prior turns out to be conjugate for canonical shuffled data problems in which the likelihood conditional on a fixed permutation can be expressed as product over the corresponding (X,Y)-pairs. Inference is based on the EM algorithm in which the intractable E-step is approximated by the Fisher-Yates algorithm. The M-step is shown to admit a significant reduction from $n^2$ to $n$ terms if the likelihood of (X,Y)-pairs has exponential family form as in the case of generalized linear models. Comparisons on synthetic and real data show that the proposed approach compares favorably to competing methods.

Interpretable machine learning (IML) becomes increasingly important in highly regulated industry sectors related to the health and safety or fundamental rights of human beings. In general, the inherently IML models should be adopted because of their transparency and explainability, while black-box models with model-agnostic explainability can be more difficult to defend under regulatory scrutiny. For assessing inherent interpretability of a machine learning model, we propose a qualitative template based on feature effects and model architecture constraints. It provides the design principles for high-performance IML model development, with examples given by reviewing our recent works on ExNN, GAMI-Net, SIMTree, and the Aletheia toolkit for local linear interpretability of deep ReLU networks. We further demonstrate how to design an interpretable ReLU DNN model with evaluation of conceptual soundness for a real case study of predicting credit default in home lending. We hope that this work will provide a practical guide of developing inherently IML models in high risk applications in banking industry, as well as other sectors.

We introduce a method for inferring and predicting latent states in the important and difficult case of state-space models where observations can only be simulated, and transition dynamics are unknown. In this setting, the likelihood of observations is not available and only synthetic observations can be generated from a black-box simulator. We propose a way of doing likelihood-free inference (LFI) of states and state prediction with a limited number of simulations. Our approach uses a multi-output Gaussian process for state inference, and a Bayesian Neural Network as a model of the transition dynamics for state prediction. We improve upon existing LFI methods for the inference task, while also accurately learning transition dynamics. The proposed method is necessary for modelling inverse problems in dynamical systems with computationally expensive simulations, as demonstrated in experiments with non-stationary user models.

This paper reviews and proposes concerns in adopting, fielding, and maintaining artificial intelligence (AI) systems. While the AI community has made rapid progress, there are challenges in certifying AI systems. Using procedures from design and operational test and evaluation, there are opportunities towards determining performance bounds to manage expectations of intended use. A notional use case is presented with image data fusion to support AI object recognition certifiability considering precision versus distance.

The Gibbard-Satterthwaite theorem states that no unanimous and non-dictatorial voting rule is strategyproof. We revisit voting rules and consider a weaker notion of strategyproofness called not obvious manipulability that was proposed by Troyan and Morrill (2020). We identify several classes of voting rules that satisfy this notion. We also show that several voting rules including k-approval fail to satisfy this property. We characterize conditions under which voting rules are obviously manipulable. One of our insights is that certain rules are obviously manipulable when the number of alternatives is relatively large compared to the number of voters. In contrast to the Gibbard-Satterthwaite theorem, many of the rules we examined are not obviously manipulable. This reflects the relatively easier satisfiability of the notion and the zero information assumption of not obvious manipulability, as opposed to the perfect information assumption of strategyproofness.

Planning the layout of bicycle-sharing stations is a complex process, especially in cities where bicycle sharing systems are just being implemented. Urban planners often have to make a lot of estimates based on both publicly available data and privately provided data from the administration and then use the Location-Allocation model popular in the field. Many municipalities in smaller cities may have difficulty hiring specialists to carry out such planning. This thesis proposes a new solution to streamline and facilitate the process of such planning by using spatial embedding methods. Based only on publicly available data from OpenStreetMap, and station layouts from 34 cities in Europe, a method has been developed to divide cities into micro-regions using the Uber H3 discrete global grid system and to indicate regions where it is worth placing a station based on existing systems in different cities using transfer learning. The result of the work is a mechanism to support planners in their decision making when planning a station layout with a choice of reference cities.

The task of assigning and validating internationally accepted commodity code (HS code) to traded goods is one of the critical functions at the customs office. This decision is crucial to importers and exporters, as it determines the tariff rate. However, similar to court decisions made by judges, the task can be non-trivial even for experienced customs officers. The current paper proposes a deep learning model to assist this seemingly challenging HS code classification. Together with Korea Customs Service, we built a decision model based on KoELECTRA that suggests the most likely heading and subheadings (i.e., the first four and six digits) of the HS code. Evaluation on 129,084 past cases shows that the top-3 suggestions made by our model have an accuracy of 95.5% in classifying 265 subheadings. This promising result implies algorithms may reduce the time and effort taken by customs officers substantially by assisting the HS code classification task.