Despite the large diffusion and use of embedding generated through Word2Vec, there are still many open questions about the reasons for its results and about its real capabilities. In particular, to our knowledge, no author seems to have analysed in detail how learning may be affected by the various choices of hyperparameters. In this work, we try to shed some light on various issues focusing on a typical dataset. It is shown that the learning rate prevents the exact mapping of the co-occurrence matrix, that Word2Vec is unable to learn syntactic relationships, and that it does not suffer from the problem of overfitting. Furthermore, through the creation of an ad-hoc network, it is also shown how it is possible to improve Word2Vec directly on the analogies, obtaining very high accuracy without damaging the pre-existing embedding. This analogy-enhanced Word2Vec may be convenient in various NLP scenarios, but it is used here as an optimal starting point to evaluate the limits of Word2Vec.

This paper considers an antenna structure where a (non-large) array of radiating elements is placed at short distance in front of a reconfigurable intelligent surface (RIS), herein nicknamed reconfigurable intelligent base station (RIBS). We firstly derive a closed-form expression for the channel between the array of radiating elements and the RIS that captures the near-field effects, and give some considerations on the channel hardening and favorable propagation in this scenario. Focusing on both active and passive RIS, we describe channel estimation and downlink signal processing techniques suitable for the RIBS structure. Additionally, we formulate and solve an optimization problem aimed at maximizing the fairness among the users with respect to the downlink power coefficients and RIS configuration both in the cases of active and passive RIBS. Numerical results show that the proposed structure is effective and capable of outperforming conventional non-RIS aided MIMO systems, especially in the case of active RIBS. The proposed antenna structure is thus shown to be able to approach massive MIMO performance levels in a cost-effective way with reduced hardware resources.

The use of estimation techniques on stochastic models to solve control problems is an emerging paradigm that falls under the rubric of Active Inference (AI) and Control as Inference (CAI). In this work, we use probability propagation on factor graphs to show that various algorithms proposed in the literature can be seen as specific composition rules in a factor graph. We show how this unified approach, presented both in probability space and in log of the probability space, provides a very general framework that includes the Sum-product, the Max-product, Dynamic programming and mixed Reward/Entropy criteria-based algorithms. The framework also expands algorithmic design options that lead to new smoother or sharper policy distributions. We propose original recursions such as: a generalized Sum/Max-product algorithm, a Smooth Dynamic programming algorithm and a modified versions of the Reward/Entropy algorithm. The discussion is carried over with reference to a path planning problem where the recursions that arise from various cost functions, although they may appear similar in scope, bear noticeable differences. We provide a comprehensive table of composition rules and a comparison through simulations, first on a synthetic small grid with a single goal with obstacles, and then on a grid extrapolated from a real-world scene with multiple goals and a semantic map.

We present a unified approach to multi-agent autonomous coordination in complex and uncertain environments, using path planning as a problem context. We start by posing the problem on a probabilistic factor graph, showing how various path planning algorithms can be translated into specific message composition rules. This unified approach provides a very general framework that, in addition to including standard algorithms (such as sum-product, max-product, dynamic programming and mixed Reward/Entropy criteria-based algorithms), expands the design options for smoother or sharper distributions (resulting in a generalized sum/max-product algorithm, a smooth dynamic programming algorithm and a modified versions of the reward/entropy recursions). The main purpose of this contribution is to extend this framework to a multi-agent system, which by its nature defines a totally different context. Indeed, when there are interdependencies among the key elements of a hybrid team (such as goals, changing mission environment, assets and threats/obstacles/constraints), interactive optimization algorithms should provide the tools for producing intelligent courses of action that are congruent with and overcome bounded rationality and cognitive biases inherent in human decision-making. Our work, using path planning as a domain of application, seeks to make progress towards this aim by providing a scientifically rigorous algorithmic framework for proactive agent autonomy.

Probability models are emerging as a promising framework to account for “intelligent” behavior. In this article, probability propagation is discussed to model agent's motion in potentially complex grids that include goals and obstacles. Tensor messages in the state-action space (due to grid structure, states are 2-D and the concomitant probability distributions are represented by 3-D arrays), propagated bi-directionally on a Markov chain, provide crucial information to guide the agent's decisions. The discussion is carried out with reference to a set of simulated grids and includes scenarios with multiple goals and multiple agents. The visualization of the tensor flow reveals interesting clues about how decisions are made by the agents. The emerging behaviors are very realistic and demonstrate great potential for the application of this framework to real environments.