Mario G. C. A. Cimino

Giulio Pisaneschi, Pierpaolo Serio, Estelle Gerbier et al.

This paper presents an experimental platform for studying intentional-state attribution toward a non-humanoid robot. The system combines a simulated robot, realistic task environments, and large language model-based explanatory layers that can express the same behavior in mentalistic, teleological, or mechanistic terms. By holding behavior constant while varying the explanatory frame, the platform provides a controlled way to investigate how language and framing shape the adoption of the intentional stance in robotics.

Federico A. Galatolo, Mario G. C. A. Cimino

This study introduces a novel approach for generating high-quality, language-specific chat corpora using a self-chat mechanism. We combine a generator LLM for creating new samples and an embedder LLM to ensure diversity. A new Masked Language Modelling (MLM) model-based quality assessment metric is proposed for evaluating and filtering the corpora. Utilizing the llama2-70b as the generator and a multilingual sentence transformer as embedder, we generate an Italian chat corpus and refine the Fauno corpus, which is based on translated English ChatGPT self-chat data. The refinement uses structural assertions and Natural Language Processing techniques. Both corpora undergo a comprehensive quality evaluation using the proposed MLM model-based quality metric. The Italian LLM fine-tuned with these corpora demonstrates significantly enhanced language comprehension and question-answering skills. The resultant model, cerbero-7b, establishes a new state-of-the-art for Italian LLMs. This approach marks a substantial advancement in the development of language-specific LLMs, with a special emphasis on augmenting corpora for underrepresented languages like Italian.

Federico A. Galatolo, Mario G. C. A. Cimino, Edoardo Cogotti

Evaluating and comparing text-to-image models is a challenging problem. Significant advances in the field have recently been made, piquing interest of various industrial sectors. As a consequence, a gold standard in the field should cover a variety of tasks and application contexts. In this paper a novel evaluation approach is experimented, on the basis of: (i) a curated data set, made by high-quality royalty-free image-text pairs, divided into ten categories; (ii) a quantitative metric, the CLIP-score, (iii) a human evaluation task to distinguish, for a given text, the real and the generated images. The proposed method has been applied to the most recent models, i.e., DALLE2, Latent Diffusion, Stable Diffusion, GLIDE and Craiyon. Early experimental results show that the accuracy of the human judgement is fully coherent with the CLIP-score. The dataset has been made available to the public.

Graziano A. Manduzio, Federico A. Galatolo, Mario G. C. A. Cimino et al.

Recent advancements in Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. While these models excel in general complex reasoning tasks, they still face challenges in mathematical problem-solving and logical reasoning. To address these limitations, researchers have explored function calling abilities, allowing LLMs to execute provided functions and utilize their outputs for task completion. However, concentrating on specific tasks can be very inefficient for large-scale LLMs to be used, because of the expensive cost of training and inference stages they need in terms of computational resources. This study introduces a novel framework for training smaller language models in function calling, focusing on specific logical and mathematical reasoning tasks. The approach aims to improve performances of small-scale models for these tasks using function calling, ensuring a high level of accuracy. Our framework employs an agent that, given a problem and a set of callable functions, queries the LLM by injecting a description and examples of the usable functions into the prompt and managing their calls in a step-by-step reasoning chain. This process is used to create a dataset of correct and incorrect reasoning chain chat completions from a large-scale LLM. This dataset is used to train a smaller LLM using Reinforcement Learning from Human Feedback (RLHF), specifically employing the Direct Preference Optimization (DPO) technique. Experimental results demonstrate how the proposed approach balances the trade-off between model size and performance, improving the ability of function calling for reasoning tasks, in smaller models.

Rambod Rahmani, Marco Parola, Mario G. C. A. Cimino

Due to the recent increase in interest in Financial Technology (FinTech), applications like credit default prediction (CDP) are gaining significant industrial and academic attention. In this regard, CDP plays a crucial role in assessing the creditworthiness of individuals and businesses, enabling lenders to make informed decisions regarding loan approvals and risk management. In this paper, we propose a workflow-based approach to improve CDP, which refers to the task of assessing the probability that a borrower will default on his or her credit obligations. The workflow consists of multiple steps, each designed to leverage the strengths of different techniques featured in machine learning pipelines and, thus best solve the CDP task. We employ a comprehensive and systematic approach starting with data preprocessing using Weight of Evidence encoding, a technique that ensures in a single-shot data scaling by removing outliers, handling missing values, and making data uniform for models working with different data types. Next, we train several families of learning models, introducing ensemble techniques to build more robust models and hyperparameter optimization via multi-objective genetic algorithms to consider both predictive accuracy and financial aspects. Our research aims at contributing to the FinTech industry in providing a tool to move toward more accurate and reliable credit risk assessment, benefiting both lenders and borrowers.

Alessio Cascione, Mattia Setzu, Federico A. Galatolo et al.

Decision-making processes in healthcare can be highly complex and challenging. Machine Learning tools offer significant potential to assist in these processes. However, many current methodologies rely on complex models that are not easily interpretable by experts. This underscores the need to develop interpretable models that can provide meaningful support in clinical decision-making. When approaching such tasks, humans typically compare the situation at hand to a few key examples and representative cases imprinted in their memory. Using an approach which selects such exemplary cases and grounds its predictions on them could contribute to obtaining high-performing interpretable solutions to such problems. To this end, we evaluate PivotTree, an interpretable prototype selection model, on an oral lesion detection problem, specifically trying to detect the presence of neoplastic, aphthous and traumatic ulcerated lesions from oral cavity images. We demonstrate the efficacy of using such method in terms of performance and offer a qualitative and quantitative comparison between exemplary cases and ground-truth prototypes selected by experts.

Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini

In this research, some of the issues that arise from the scalarization of the multi-objective optimization problem in the Advantage Actor Critic (A2C) reinforcement learning algorithm are investigated. The paper shows how a naive scalarization can lead to gradients overlapping. Furthermore, the possibility that the entropy regularization term can be a source of uncontrolled noise is discussed. With respect to the above issues, a technique to avoid gradient overlapping is proposed, while keeping the same loss formulation. Moreover, a method to avoid the uncontrolled noise, by sampling the actions from distributions with a desired minimum entropy, is investigated. Pilot experiments have been carried out to show how the proposed method speeds up the training. The proposed approach can be applied to any Advantage-based Reinforcement Learning algorithm.

Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini

In this paper, a novel architecture of Recurrent Neural Network (RNN) is designed and experimented. The proposed RNN adopts a computational memory based on the concept of stigmergy. The basic principle of a Stigmergic Memory (SM) is that the activity of deposit/removal of a quantity in the SM stimulates the next activities of deposit/removal. Accordingly, subsequent SM activities tend to reinforce/weaken each other, generating a coherent coordination between the SM activities and the input temporal stimulus. We show that, in a problem of supervised classification, the SM encodes the temporal input in an emergent representational model, by coordinating the deposit, removal and classification activities. This study lays down a basic framework for the derivation of a SM-RNN. A formal ontology of SM is discussed, and the SM-RNN architecture is detailed. To appreciate the computational power of an SM-RNN, comparative NNs have been selected and trained to solve the MNIST handwritten digits recognition benchmark in its two variants: spatial (sequences of bitmap rows) and temporal (sequences of pen strokes).

A. L. Alfeo, F. P. Appio, M. G. C. A. Cimino et al.

Regional innovation is more and more considered an important enabler of welfare. It is no coincidence that the European Commission has started looking at regional peculiarities and dynamics, in order to focus Research and Innovation Strategies for Smart Specialization towards effective investment policies. In this context, this work aims to support policy makers in the analysis of innovation-relevant trends. We exploit a European database of the regional patent application to determine the dynamics of a set of technological innovation indicators. For this purpose, we design and develop a software system for assessing unfolding trends in such indicators. In contrast with conventional knowledge-based design, our approach is biologically-inspired and based on self-organization of information. This means that a functional structure, called track, appears and stays spontaneous at runtime when local dynamism in data occurs. A further prototyping of tracks allows a better distinction of the critical phenomena during unfolding events, with a better assessment of the progressing levels. The proposed mechanism works if structural parameters are correctly tuned for the given historical context. Determining such correct parameters is not a simple task since different indicators may have different dynamics. For this purpose, we adopt an adaptation mechanism based on differential evolution. The study includes the problem statement and its characterization in the literature, as well as the proposed solving approach, experimental setting and results.

A. L. Alfeo, M. G. C. A. Cimino, G. Vaglini

Physical activity level (PAL) in older adults can enhance healthy aging, improve functional capacity, and prevent diseases. It is known that human annotations of PAL can be affected by subjectivity and inaccuracy. Recently developed smart devices can allow a non-invasive, analytic, and continuous gathering of physiological signals. We present an innovative computational system fed by signals of heartbeat rate, wrist motion and pedometer sensed by a smartwatch. More specifically, samples of each signal are aggregated by functional structures called trails. The trailing process is inspired by stigmergy, an insects' coordination mechanism, and is managed by computational units called stigmergic receptive fields (SRFs). SRFs, which compute the similarity between trails, are arranged in a stigmergic perceptron to detect a collection of micro-behaviours of the raw signal, called archetypes. A SRF is adaptive to subjects: its structural parameters are tuned by a differential evolution algorithm. SRFs are used in a multilayer architecture, providing further levels of processing to realize macro analyses in the application domain. As a result, the architecture provides a daily PAL, useful to detect behavioural shift indicating initial signs of disease or deviations in performance. As a proof of concept, the approach has been experimented on three subjects.

Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini

A current research trend in neurocomputing involves the design of novel artificial neural networks incorporating the concept of time into their operating model. In this paper, a novel architecture that employs stigmergy is proposed. Computational stigmergy is used to dynamically increase (or decrease) the strength of a connection, or the activation level, of an artificial neuron when stimulated (or released). This study lays down a basic framework for the derivation of a stigmergic NN with a related training algorithm. To show its potential, some pilot experiments have been reported. The XOR problem is solved by using only one single stigmergic neuron with one input and one output. A static NN, a stigmergic NN, a recurrent NN and a long short-term memory NN have been trained to solve the MNIST digits recognition benchmark.

Antonio L. Alfeo, Mario G. C. A. Cimino, Sara Egidi et al.

A key aspect of a sustainable urban transportation system is the effectiveness of transportation policies. To be effective, a policy has to consider a broad range of elements, such as pollution emission, traffic flow, and human mobility. Due to the complexity and variability of these elements in the urban area, to produce effective policies remains a very challenging task. With the introduction of the smart city paradigm, a widely available amount of data can be generated in the urban spaces. Such data can be a fundamental source of knowledge to improve policies because they can reflect the sustainability issues underlying the city. In this context, we propose an approach to exploit urban positioning data based on stigmergy, a bio-inspired mechanism providing scalar and temporal aggregation of samples. By employing stigmergy, samples in proximity with each other are aggregated into a functional structure called trail. The trail summarizes relevant dynamics in data and allows matching them, providing a measure of their similarity. Moreover, this mechanism can be specialized to unfold specific dynamics. Specifically, we identify high-density urban areas (i.e hotspots), analyze their activity over time, and unfold anomalies. Moreover, by matching activity patterns, a continuous measure of the dissimilarity with respect to the typical activity pattern is provided. This measure can be used by policy makers to evaluate the effect of policies and change them dynamically. As a case study, we analyze taxi trip data gathered in Manhattan from 2013 to 2015.

Antonio L. Alfeo, Mario G. C. A. Cimino, Sara Egidi et al.

Positioning data offer a remarkable source of information to analyze crowds urban dynamics. However, discovering urban activity patterns from the emergent behavior of crowds involves complex system modeling. An alternative approach is to adopt computational techniques belonging to the emergent paradigm, which enables self-organization of data and allows adaptive analysis. Specifically, our approach is based on stigmergy. By using stigmergy each sample position is associated with a digital pheromone deposit, which progressively evaporates and aggregates with other deposits according to their spatiotemporal proximity. Based on this principle, we exploit positioning data to identify high density areas (hotspots) and characterize their activity over time. This characterization allows the comparison of dynamics occurring in different days, providing a similarity measure exploitable by clustering techniques. Thus, we cluster days according to their activity behavior, discovering unexpected urban activity patterns. As a case study, we analyze taxi traces in New York City during 2015.