The advancements in human-centered artificial intelligence (HCAI) systems for Industry 5.0 is a new phase of industrialization that places the worker at the center of the production process and uses new technologies to increase prosperity beyond jobs and growth. HCAI presents new objectives that were unreachable by either humans or machines alone, but this also comes with a new set of challenges. Our proposed method accomplishes this through the knowlEdge architecture, which enables human operators to implement AI solutions using a zero-touch framework. It relies on containerized AI model training and execution, supported by a robust data pipeline and rounded off with human feedback and evaluation interfaces. The result is a platform built from a number of components, spanning all major areas of the AI lifecycle. We outline both the architectural concepts and implementation guidelines and explain how they advance HCAI systems and Industry 5.0. In this article, we address the problems we encountered while implementing the ideas within the edge-to-cloud continuum. Further improvements to our approach may enhance the use of AI in Industry 5.0 and strengthen trust in AI systems.

The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last few years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we apply an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first use case of policy graphs in the context of explaining agent behaviour in cooperative multi-agent scenarios and present experimental results that sets this kind of scenario apart from previous implementations in single-agent scenarios: when requiring cooperative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations.

Bias detection in the computer vision field is a necessary task, to achieve fair models. These biases are usually due to undesirable correlations present in the data and learned by the model. Although explainability can be a way to gain insights into model behavior, reviewing explanations is not straightforward. This work proposes a methodology to analyze the model biases without using explainability. By doing so, we reduce the potential noise arising from explainability methods, and we minimize human noise during the analysis of explanations. The proposed methodology combines images of the original distribution with images of potential context biases and analyzes the effect produced in the model’s output. For this work, we first presented and released three new datasets generated by diffusion models. Next, we used the proposed methodology to analyze the context impact on the model’s prediction. Finally, we verified the reliability of the proposed methodology and the consistency of its results. We hope this tool will help practitioners to detect and mitigate potential biases, allowing them to obtain more reliable models.

The adoption of AI in manufacturing enables numerous benefits that can significantly impact productivity, efficiency, and decision-making processes. AI algorithms can optimize production schedules, inventory management, and supply chain operations by analyzing historical data and producing demand forecasts. In spite of these benefits, some challenges such as integration, lack of data infrastructure and expertise, and resistance to change need to be addressed for the industry to successfully adopt AI. To overcome these issues, we introduce the AI Model Generation framework (AMG), able to automatically generate AI models that adjust to the user’s needs. More precisely, the model development process involves the execution of a whole chain of sub-processes, including data loading, automated data pre-processing, cost computation, automatic model hyperparameter tuning, training, inference, explainability generation, standardization, and containerization. We expect our approach to aid non-expert users into more effectively producing machine and deep learning algorithms and hyperparameter settings that are appropriate to solve their problems without sacrificing privacy and relying on third-party services and infrastructure as few as possible. Keywords AutoML Explainability (XAI) Hyperparameter tuning Pre-processing Standardization Model deployment

AI explainability improves the transparency of models, making them more trustworthy. Such goals are motivated by the emergence of deep learning models, which are obscure by nature; even in the domain of images, where deep learning has succeeded the most, explainability is still poorly assessed. In the field of image recognition many feature attribution methods have been proposed with the purpose of explaining a model's behavior using visual cues. However, no metrics have been established so far to assess and select these methods objectively. In this paper we propose a consistent evaluation score for feature attribution methods -- the Focus -- designed to quantify their coherency to the task. While most previous work adds out-of-distribution noise to samples, we introduce a methodology to add noise from within the distribution. This is done through mosaics of instances from different classes, and the explanations these generate. On those, we compute a visual pseudo-precision metric, Focus. First, we show the robustness of the approach through a set of randomization experiments. Then we use Focus to compare six popular explainability techniques across several CNN architectures and classification datasets. Our results find some methods to be consistently reliable (LRP, GradCAM), while others produce class-agnostic explanations (SmoothGrad, IG). Finally we introduce another application of Focus, using it for the identification and characterization of biases found in models. This empowers bias-management tools, in another small step towards trustworthy AI.

This paper addresses the critical issue of trust in Artificial Intelligence systems, especially when users might find it challenging to comprehend the internal decision-making processes of such systems. A relevant topic of research in this respect is Theory of Mind, which involves attempting to understand these systems as if they possessed beliefs, desires, and intentions. We focus on the latter: intentions, and we examine how producing explanations based on them can improve \emph{understandability} while allowing for a better interpretation of how they align with human values. We also review some existing methods for identifying intentions in AI systems and we conclude with a discussion on possible future directions in this line of research.