Search

Artificial intelligence (AI) has been embedded into many aspects of people's daily lives and it has become normal for people to have AI make decisions for them. Reinforcement learning (RL) models increase the space of solvable problems with respect to other machine learning paradigms. Some of the most interesting applications are in situations with non-differentiable expected reward function, operating in unknown or underdefined environment, as well as for algorithmic discovery that surpasses performance of any teacher, whereby agent learns from experimental experience through simple feedback. The range of applications and their social impact is vast, just to name a few: genomics, game-playing (chess, Go, etc.), general optimization, financial investment, governmental policies, self-driving cars, recommendation systems, etc. It is therefore essential to improve the trust and transparency of RL-based systems through explanations. Most articles dealing with explainability in artificial intelligence provide methods that concern supervised learning and there are very few articles dealing with this in the area of RL. The reasons for this are the credit assignment problem, delayed rewards, and the inability to assume that data is independently and identically distributed (i.i.d.). This position paper attempts to give a systematic overview of existing methods in the explainable RL area and propose a novel unified taxonomy, building and expanding on the existing ones. The position section describes pragmatic aspects of how explainability can be observed. The gap between the parties receiving and generating the explanation is especially emphasized. To reduce the gap and achieve honesty and truthfulness of explanations, we set up three pillars: proactivity, risk attitudes, and epistemological constraints. To this end, we illustrate our proposal on simple variants of the shortest path problem., Comment: 18 pages, 4 figures, 76 references. keywords: explainable artificial intelligence, explainable reinforcement learning, XRL, XAI, risk attitudes, epistemic AI, proactivity

Recent decades have seen a rise in the use of physics methods to study different societal phenomena. This development has been due to physicists venturing outside of their traditional domains of interest, but also due to scientists from other disciplines taking from physics the methods that have proven so successful throughout the 19th and the 20th century. Here we dub this field 'social physics' and pay our respect to intellectual mavericks who nurtured it to maturity. We do so by reviewing the current state of the art. Starting with a set of topics that are at the heart of modern human societies, we review research dedicated to urban development and traffic, the functioning of financial markets, cooperation as the basis for our evolutionary success, the structure of social networks, and the integration of intelligent machines into these networks. We then shift our attention to a set of topics that explore potential threats to society. These include criminal behaviour, large-scale migrations, epidemics, environmental challenges, and climate change. We end the coverage of each topic with promising directions for future research. Based on this, we conclude that the future for social physics is bright. Physicists studying societal phenomena are no longer a curiosity, but rather a force to be reckoned with. Notwithstanding, it remains of the utmost importance that we continue to foster constructive dialogue and mutual respect at the interfaces of different scientific disciplines., Comment: 359 pages, 78 figures; published in Physics Reports

Coastal water quality management is a public health concern, as poor coastal water quality can harbor pathogens that are dangerous to human health. Tourism-oriented countries need to actively monitor the condition of coastal water at tourist popular sites during the summer season. In this study, routine monitoring data of $Escherichia\ Coli$ and enterococci across 15 public beaches in the city of Rijeka, Croatia, were used to build machine learning models for predicting their levels based on environmental parameters as well as to investigate their relationships with environmental stressors. Gradient Boosting (Catboost, Xgboost), Random Forests, Support Vector Regression and Artificial Neural Networks were trained with measurements from all sampling sites and used to predict $E.\ Coli$ and enterococci values based on environmental features. The evaluation of stability and generalizability with 10-fold cross validation analysis of the machine learning models, showed that the Catboost algorithm performed best with R$^2$ values of 0.71 and 0.68 for predicting $E.\ Coli$ and enterococci, respectively, compared to other evaluated ML algorithms including Xgboost, Random Forests, Support Vector Regression and Artificial Neural Networks. We also use the SHapley Additive exPlanations technique to identify and interpret which features have the most predictive power. The results show that site salinity measured is the most important feature for forecasting both $E.\ Coli$ and enterococci levels. Finally, the spatial and temporal accuracy of both ML models were examined at sites with the lowest coastal water quality. The spatial $E. Coli$ and enterococci models achieved strong R$^2$ values of 0.85 and 0.83, while the temporal models achieved R$^2$ values of 0.74 and 0.67. The temporal model also achieved moderate R$^2$ values of 0.44 and 0.46 at a site with high coastal water quality.

In this study, we investigated the inhibition of SARS-CoV-2 spike glycoprotein with HIV drugs and their combinations. This glycoprotein is essential for the reproduction of the SARS-COV-2 virus, so its inhibition opens new avenues for the treatment of patients with COVID-19 disease. In doing so, we used the VINI in silico model of cancer, whose high accuracy in finding effective drugs and their combinations was confirmed in vitro by comparison with existing results from NCI-60 bases, and in vivo by comparison with existing clinical trial results. In the first step, the VINI model calculated the inhibition efficiency of SARS-CoV-2 spike glycoprotein with 44 FDA-approved antiviral drugs. Of these drugs, HIV drugs have been shown to be effective, while others mainly have shown weak or no efficiency. Subsequently, the VINI model calculated the inhibition efficiency of all possible double and triple HIV drug combinations, and among them identified ten with the highest inhibition efficiency. These ten combinations were analyzed by Medscape drug-drug interaction software and LexiComp Drug Interactions. All combinations except the combination of cobicistat_abacavir_rilpivirine appear to have serious interactions (risk rating category D) when dosage adjustments/reductions are required for possible toxicity. Finally, the VINI model compared the inhibition efficiency of cobicistat_abacivir_rilpivirine combination with cocktails and individual drugs already used or planned to be tested against SARS-CoV-2. Combination cobicistat_abacivir_rilpivirine demonstrated the highest inhibition of SARS-CoV-2 spike glycoprotein over others. Thus, this combination seems to be a promising candidate for the further in vitro testing and clinical trials., Comment: 8 pages, 4 figures

In this paper, we present a novel method for analysis and segmentation of laminar structure of the cortex based on tissue characteristics whose change across the gray matter underlies distinctive between cortical layers. We develop and analyze features of individual neurons to investigate changes in cytoarchitectonic differentiation and present a novel high-performance, automated framework for neuron-level histological image analysis. Local tissue and cell descriptors such as density, neuron size and other measures are used for development of more complex neuron features used in machine learning model trained on data manually labeled by three human experts. Final neuron layer classifications were obtained by training a separate model for each expert and combining their probability outputs. Importances of developed neuron features on both global model level and individual prediction level are presented and discussed.

Real-world attacks can be interpreted as the result of competitive interactions between networks, ranging from predator-prey networks to networks of countries under economic sanctions. Although the purpose of an attack is to damage a target network, it also curtails the ability of the attacker, which must choose the duration and magnitude of an attack to avoid negative impacts on its own functioning. Nevertheless, despite the large number of studies on interconnected networks, the consequences of initiating an attack have never been studied. Here, we address this issue by introducing a model of network competition where a resilient network is willing to partially weaken its own resilience in order to more severely damage a less resilient competitor. The attacking network can take over the competitor nodes after their long inactivity. However, due to a feedback mechanism the takeovers weaken the resilience of the attacking network. We define a conservation law that relates the feedback mechanism to the resilience dynamics for two competing networks. Within this formalism, we determine the cost and optimal duration of an attack, allowing a network to evaluate the risk of initiating hostilities., Comment: 8 two-column pages, 6 figures, supplementary material; accepted for publication in Journal of the Royal Society Interface