We introduce multi-goal multi agent path finding (MAPF$^{MG}$) which generalizes the standard discrete multi-agent path finding (MAPF) problem. While the task in MAPF is to navigate agents in an undirected graph from their starting vertices to one individual goal vertex per agent, MAPF$^{MG}$ assigns each agent multiple goal vertices and the task is to visit each of them at least once. Solving MAPF$^{MG}$ not only requires finding collision free paths for individual agents but also determining the order of visiting agent's goal vertices so that common objectives like the sum-of-costs are optimized. We suggest two novel algorithms using different paradigms to address MAPF$^{MG}$: a heuristic search-based search algorithm called Hamiltonian-CBS (HCBS) and a compilation-based algorithm built using the SMT paradigm, called SMT-Hamiltonian-CBS (SMT-HCBS). Experimental comparison suggests limitations of compilation-based approach.

During the first step of practical reasoning, i.e. deliberation, an intelligent agent generates a set of pursuable goals and then selects which of them he commits to achieve. An intelligent agent may in general generate multiple pursuable goals, which may be incompatible among them. In this paper, we focus on the definition, identification and resolution of these incompatibilities. The suggested approach considers the three forms of incompatibility introduced by Castelfranchi and Paglieri, namely the terminal incompatibility, the instrumental or resources incompatibility and the superfluity. We characterise computationally these forms of incompatibility by means of arguments that represent the plans that allow an agent to achieve his goals. Thus, the incompatibility among goals is defined based on the conflicts among their plans, which are represented by means of attacks in an argumentation framework. We also work on the problem of goals selection; we propose to use abstract argumentation theory to deal with this problem, i.e. by applying argumentation semantics. We use a modified version of the "cleaner world" scenario in order to illustrate the performance of our proposal.

Recent studies on the weight space of deep neural networks [1, 2] have highlighted the existence of rare subdominant clusters of configurations which yield a high test accuracy. Although these clusters constitute a deviation from typicality, they are efficiently encountered by stochastic gradient descent (SGD) algorithms and correspond to wide valleys of suitable loss functions, such as cross entropy [3]. An analogous circumstance occurs in the context of constraint satisfaction problems, where the chase after clusters of solutions is improved when the loss function gets supplemented by a term that encourages a local high density of solutions [4]. In order to find the number of solutions contained in a vicinity of a specific weight configuration, one can define a local solution-counting functional, namely, a local entropy. Classification tasks performed by means of quantized neural networks (where the weights are discrete) can be interpreted as constraint satisfaction problems. There are however two reasons to generalize the concept of local entropy: First, classification problems are typically required to reach a high but not necessarily perfect accuracy; second, they are often approached with machines that have continuous weights.

Graph neural networks (GNNs) have been shown with superior performance in various applications, but training dedicated GNNs can be costly for large-scale graphs. Some recent work started to study the pre-training of GNNs. However, none of them provide theoretical insights into the design of their frameworks, or clear requirements and guarantees towards the transferability of GNNs. In this work, we establish a theoretically grounded and practically useful framework for the transfer learning of GNNs. Firstly, we propose a novel view towards the essential graph information and advocate the capturing of it as the goal of transferable GNN training, which motivates the design of Ours, a novel GNN framework based on ego-graph information maximization to analytically achieve this goal. Secondly, we specify the requirement of structure-respecting node features as the GNN input, and derive a rigorous bound of GNN transferability based on the difference between the local graph Laplacians of the source and target graphs. Finally, we conduct controlled synthetic experiments to directly justify our theoretical conclusions. Extensive experiments on real-world networks towards role identification show consistent results in the rigorously analyzed setting of direct-transfering, while those towards large-scale relation prediction show promising results in the more generalized and practical setting of transfering with fine-tuning.

Model selection is a fundamental part of Bayesian statistical inference; a widely used tool in the field of epidemiology. Simple methods such as Akaike Information Criterion are commonly used but they do not incorporate the uncertainty of the model's parameters, which can give misleading choices when comparing models with similar fit to the data. One approach to model selection in a more rigorous way that uses the full posterior distributions of the models is to compute the ratio of the normalising constants (or model evidence), known as Bayes factors. These normalising constants integrate the posterior distribution over all parameters and balance over and under fitting. However, normalising constants often come in the form of intractable, high-dimensional integrals, therefore special probabilistic techniques need to be applied to correctly estimate the Bayes factors. One such method is thermodynamic integration (TI), which can be used to estimate the ratio of two models' evidence by integrating over a continuous path between the two un-normalised densities. In this paper we introduce a variation of the TI method, here referred to as referenced TI, which computes a single model's evidence in an efficient way by using a reference density such as a multivariate normal - where the normalising constant is known. We show that referenced TI, an asymptotically exact Monte Carlo method of calculating the normalising constant of a single model, in practice converges to the correct result much faster than other competing approaches such as the method of power posteriors. We illustrate the implementation of the algorithm on informative 1- and 2-dimensional examples, and apply it to a popular linear regression problem, and use it to select parameters for a model of the COVID-19 epidemic in South Korea.

ModelOp, a leading provider of ModelOps solutions, announced it has been recognized in reports by industry analyst Gartner and included in the Forrester paper on the new and fast growing ModelOps market. As enterprises become increasingly reliant on AI models to help them transform and reimagine business, the challenges of managing AI models is on the rise. According to Forrester research report, organizations must employ new ModelOps capabilities if they want to operate AI models at scale. Gartner analysts report, "it is to be noted that ModelOps lies at the heart of any enterprise AI strategy." In addition, "ModelOps is about creating a shared service that runs across the organization – enabling robust scaling, governance, integration, monitoring and management of various AI models. Adopting a ModelOps strategy should facilitate improvements to the performance, scalability and reliability of AI models."

This article was reviewed by Renato Ambrósio, Jr, MD, PhD Ectasia is an intriguing and mysterious complication of laser-vision-correction (LVC) procedures. The potentially devastating problem underscores the importance of determining the susceptibility of the cornea for developing progressive ectasia, and of going beyond detecting just mild or subclinical keratoconus. The corneal structure as well as the potential impact of LVC should be considered to predict ectasia risk in every patient. "The LVC procedure and eye rubbing are the primary environmental culprits in the development of ectasia in any cornea," said Renato Ambrósio, Jr, MD, PhD. "So, a basic factor for avoiding ectasia is educating the patient not to rub the eye."

Currently, unmanned aerial vehicles, such as drones, are becoming a part of our lives and reaching out to many areas of society, including the industrialized world. A common alternative to control the movements and actions of the drone is through unwired tactile interfaces, for which different remote control devices can be found. However, control through such devices is not a natural, human-like communication interface, which sometimes is difficult to master for some users. In this work, we present a domain-based speech recognition architecture to effectively control an unmanned aerial vehicle such as a drone. The drone control is performed using a more natural, human-like way to communicate the instructions. Moreover, we implement an algorithm for command interpretation using both Spanish and English languages, as well as to control the movements of the drone in a simulated domestic environment. The conducted experiments involve participants giving voice commands to the drone in both languages in order to compare the effectiveness of each of them, considering the mother tongue of the participants in the experiment. Additionally, different levels of distortion have been applied to the voice commands in order to test the proposed approach when facing noisy input signals. The obtained results show that the unmanned aerial vehicle is capable of interpreting user voice instructions achieving an improvement in speech-to-action recognition for both languages when using phoneme matching in comparison to only using the cloud-based algorithm without domain-based instructions. Using raw audio inputs, the cloud-based approach achieves 74.81% and 97.04% accuracy for English and Spanish instructions respectively, whereas using our phoneme matching approach the results are improved achieving 93.33% and 100.00% accuracy for English and Spanish languages.

MLassisted applications are a trend, and many researchers and developers are rushing to apply ML and recover their inherent potential benefits [2] [3]. However, using ML techniques to solve any problem do require some previous background and expertise. For example, it is vital to choose the ML technique that better suits the target application in terms of available computational capability and expected target results. In sequence to an adequate ML technique choice, it is typically necessary to model the problem under the premises of the chosen technique. The modeling process may include, as an example, an MDP-based markovian process (Markov Decision Process) like Q-Learning or SARSA formulation for Reinforcement Learning or the definition of a neural network structure for Neural Networks (NN) [4] [5].

Narratives are fundamental to our perception of the world and are pervasive in all activities that involve the representation of events in time. Yet, modern online information systems do not incorporate narratives in their representation of events occurring over time. This article aims to bridge this gap, combining the theory of narrative representations with the data from modern online systems. We make three key contributions: a theory-driven computational representation of narratives, a novel extraction algorithm to obtain these representations from data, and an evaluation of our approach. In particular, given the effectiveness of visual metaphors, we employ a route map metaphor to design a narrative map representation. The narrative map representation illustrates the events and stories in the narrative as a series of landmarks and routes on the map. Each element of our representation is backed by a corresponding element from formal narrative theory, thus providing a solid theoretical background to our method. Our approach extracts the underlying graph structure of the narrative map using a novel optimization technique focused on maximizing coherence while respecting structural and coverage constraints. We showcase the effectiveness of our approach by performing a user evaluation to assess the quality of the representation, metaphor, and visualization. Evaluation results indicate that the Narrative Map representation is a powerful method to communicate complex narratives to individuals. Our findings have implications for intelligence analysts, computational journalists, and misinformation researchers.