Vangelis Karkaletsis

Eleonora Ricci, George Giannakopoulos, Vangelis Karkaletsis et al.

Coarse graining (CG) enables the investigation of molecular properties for larger systems and at longer timescales than the ones attainable at the atomistic resolution. Machine learning techniques have been recently proposed to learn CG particle interactions, i.e. develop CG force fields. Graph representations of molecules and supervised training of a graph convolutional neural network architecture are used to learn the potential of mean force through a force matching scheme. In this work, the force acting on each CG particle is correlated to a learned representation of its local environment that goes under the name of SchNet, constructed via continuous filter convolutions. We explore the application of SchNet models to obtain a CG potential for liquid benzene, investigating the effect of model architecture and hyperparameters on the thermodynamic, dynamical, and structural properties of the simulated CG systems, reporting and discussing challenges encountered and future directions envisioned.

Christos Sevastopoulos, Joey Hussain, Stasinos Konstantopoulos et al.

Accurate indoor free-space segmentation is a challenging task due to the complexity and the dynamic nature that indoor environments exhibit. We propose an indoors free-space segmentation method that associates large depth values with navigable regions. Our method leverages an unsupervised masking technique that, using positive instances, generates segmentation labels based on textural homogeneity and depth uniformity. Moreover, we generate superpixels corresponding to areas of higher depth and align them with features extracted from a Dense Prediction Transformer (DPT). Using the estimated free-space masks and the DPT feature representation, a SegFormer model is fine-tuned on our custom-collected indoor dataset. Our experiments demonstrate sufficient performance in intricate scenarios characterized by cluttered obstacles and challenging identification of free space.

Michael Papademas, Xenia Ziouvelou, Antonis Troumpoukis et al.

Artificial Intelligence (AI) technology epitomizes the complex challenges posed by human-made artifacts, particularly those widely integrated into society and exerting significant influence, highlighting potential benefits and their negative consequences. While other technologies may also pose substantial risks, AI's pervasive reach makes its societal effects especially profound. The complexity of AI systems, coupled with their remarkable capabilities, can lead to a reliance on technologies that operate beyond direct human oversight or understanding. To mitigate the risks that arise, several theoretical tools and guidelines have been developed, alongside efforts to create technological tools aimed at safeguarding Trustworthy AI. The guidelines take a more holistic view of the issue but fail to provide techniques for quantifying trustworthiness. Conversely, while technological tools are better at achieving such quantification, they lack a holistic perspective, focusing instead on specific aspects of Trustworthy AI. This paper aims to introduce an assessment method that combines the ethical components of Trustworthy AI with the algorithmic processes of PageRank and TrustRank. The goal is to establish an assessment framework that minimizes the subjectivity inherent in the self-assessment techniques prevalent in the field by introducing algorithmic criteria. The application of our approach indicates that a holistic assessment of an AI system's trustworthiness can be achieved by providing quantitative insights while considering the theoretical content of relevant guidelines.

Athanasios Davvetas, Iraklis A. Klampanos, Vangelis Karkaletsis

In this paper we introduce evidence transfer for clustering, a deep learning method that can incrementally manipulate the latent representations of an autoencoder, according to external categorical evidence, in order to improve a clustering outcome. By evidence transfer we define the process by which the categorical outcome of an external, auxiliary task is exploited to improve a primary task, in this case representation learning for clustering. Our proposed method makes no assumptions regarding the categorical evidence presented, nor the structure of the latent space. We compare our method, against the baseline solution by performing k-means clustering before and after its deployment. Experiments with three different kinds of evidence show that our method effectively manipulates the latent representations when introduced with real corresponding evidence, while remaining robust when presented with low quality evidence.

Iraklis A. Klampanos, Athanasios Davvetas, Antonis Koukourikos et al.

Deep learning models, while effective and versatile, are becoming increasingly complex, often including multiple overlapping networks of arbitrary depths, multiple objectives and non-intuitive training methodologies. This makes it increasingly difficult for researchers and practitioners to design, train and understand them. In this paper we present ANNETT-O, a much-needed, generic and computer-actionable vocabulary for researchers and practitioners to describe their deep learning configurations, training procedures and experiments. The proposed ontology focuses on topological, training and evaluation aspects of complex deep neural configurations, while keeping peripheral entities more succinct. Knowledge bases implementing ANNETT-O can support a wide variety of queries, providing relevant insights to users. In addition to a detailed description of the ontology, we demonstrate its suitability to the task via a number of hypothetical use-cases of increasing complexity.

I. A. Klampanos, A. Davvetas, S. Andronopoulos et al.

Emergency response applications for nuclear or radiological events can be significantly improved via deep feature learning due to the hidden complexity of the data and models involved. In this paper we present a novel methodology for rapid source estimation during radiological releases based on deep feature extraction and weather clustering. Atmospheric dispersions are then calculated based on identified predominant weather patterns and are matched against simulated incidents indicated by radiation readings on the ground. We evaluate the accuracy of our methods over multiple years of weather reanalysis data in the European region. We juxtapose these results with deep classification convolution networks and discuss advantages and disadvantages.

N. Mavridis, S. Konstantopoulos, I. Vetsikas et al.

Traditional Artificial Cognitive Systems (for example, intelligent robots) share a number of limitations. First, they are usually made up only of machine components; humans are only playing the role of user or supervisor. And yet, there are tasks in which the current state of the art of AI has much worse performance or is more expensive than humans: thus, it would be highly beneficial to have a systematic way of creating systems with both human and machine components, possibly with remote non-expert humans providing short-duration real-time services. Second, their components are often dedicated to only one system, and underutilized for a big part of their lifetime. Third, there is no inherent support for robust operation, and if a new better component becomes available, one cannot easily replace the old component. Fourth, they are viewed as a resource to be developed and owned, not as a utility. Thus, we are presenting CLIC: a framework for constructing cognitive systems that overcome the above limitations. The architecture of CLIC provides specific mechanisms for creating and operating cognitive systems that fulfill a set of desiderata: First, that are distributed yet situated, interacting with the physical world though sensing and actuation services, and that are also combining human as well as machine services. Second, that are made up of components that are time-shared and re-usable. Third, that provide increased robustness through self-repair. Fourth, that are constructed and reconstructed on the fly, with components that dynamically enter and exit the system during operation, on the basis of availability, pricing, and need. Importantly, fifth, the cognitive systems created and operated by CLIC do not need to be owned and can be provided on demand, as a utility; thus transforming human-machine situated intelligence to a service, and opening up many interesting opportunities.