Giovanni Ciatto

Giovanni Ciatto
University of Bologna | UNIBO · Department of Computer Science and Engineering DISI

PhD Student in Data Science & Computation @ UniBO

About

45
Publications
7,143
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
299
Citations
Citations since 2016
45 Research Items
295 Citations
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100
2016201720182019202020212022020406080100

Publications

Publications (45)
Conference Paper
We propose a novel method to inject symbolic knowledge in form of Datalog formulae into neural networks (NN), called KINS (Knowledge Injection via Network Structuring). The idea behind our method is to extend NN internal structure with ad-hoc layers built out the injected symbolic knowledge. KINS does not constrain NN to any specific architecture,...
Chapter
Modern distributed systems require communicating agents to agree on a shared, formal semantics for the data they exchange and operate upon. The Semantic Web offers tools to encode semantics in the form of ontologies, where data is represented in the form of knowledge graphs (KG). Applying such tools to intelligent agents equipped with machine learn...
Chapter
A long-standing ambition in artificial intelligence is to integrate predictors’ inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from symbolic knowledge). Many methods in the literature support injection of symbolic knowledge into predictors, generally following the purpose of attaining better...
Article
A common practice in modern explainable AI is to post-hoc explain black-box machine learning (ML) predictors – such as neural networks – by extracting symbolic knowledge out of them, in the form of either rule lists or decision trees. By acting as a surrogate model, the extracted knowledge aims at revealing the inner working of the black box, thus...
Article
Full-text available
Both logic programming in general and Prolog in particular have a long and fascinating history, intermingled with that of many disciplines they inherited from or catalyzed. A large body of research has been gathered over the last 50 years, supported by many Prolog implementations. Many implementations are still actively developed, while new ones ke...
Preprint
(Under consideration for publication in Theory and Practice of Logic Programming) Both logic programming in general, and Prolog in particular, have a long and fascinating history, inter-mingled with that of many disciplines they inherited from or catalyzed. A large body of research has been gathered over the last 50 years, supported by many Prolog...
Conference Paper
Full-text available
The work introduces an elastic and platform-agnostic approach to probabilistic logic programming aimed at linking this paradigm with modern mainstream programming platforms, thus widening its usability and portability (e.g. towards the JVM, Android, Python, and JavaScript platforms). We design our solution as an extension of the 2P-Kt symbolic AI e...
Article
To date, logic-based technologies are either built on top or as extensions of the Prolog language, mostly working as monolithic solutions tailored upon specific inference procedures, unification mechanisms, or knowledge representation techniques. Instead, to maximise their impact, logic-based technologies should support and enable the general-purpo...
Chapter
Full-text available
Explainable AI (XAI) has emerged in recent years as a set of techniques and methodologies to interpret and explain machine learning (ML) predictors. To date, many initiatives have been proposed. Nevertheless, current research efforts mainly focus on methods tailored to specific ML tasks and algorithms, such as image classification and sentiment ana...
Chapter
Full-text available
Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue. Intelligent software agents can behave intelligently in well-defined scenarios, relying o...
Chapter
Knowledge-extraction methods are applied to ML-based predictors to attain explainable representations of their operation when the lack of interpretable results constitutes a problem. Several algorithms have been proposed for knowledge extraction, mostly focusing on the extraction of either lists or trees of rules. Yet, most of them only support sup...
Chapter
Recently, the Deep Learning (DL) research community has focused on developing efficient and highly performing Neural Networks (NN). Meanwhile, the eXplainable AI (XAI) research community has focused on making Machine Learning (ML) and Deep Learning methods interpretable and transparent, seeking explainability. This work is a preliminary study on th...
Conference Paper
Knowledge extraction methods are applied to ML-based predictors to attain explainable representations of their functioning when the lack of interpretable results constitutes a problem. Several algorithms have been proposed for knowledge extraction, mostly focusing on the extraction of either lists or trees of rules. Yet, most of them only support s...
Conference Paper
Recently, the Deep Learning (DL) research community has focused on developing efficient and highly performing Neural Networks (NN). Meanwhile, the eXplainable AI (XAI) research community has fo-cused on making Machine Learning (ML) and Deep Learning methods interpretable and transparent, seeking explainability. This work is a preliminary study on t...
Conference Paper
Full-text available
Since their appearance, computer programs have embodied discipline and structured approaches and methodologies. Yet, to this day, equipping machines with imaginative and creative capabilities remains one of the most challenging and fascinating goals we pursue. Intelligent software agents can behave intelligently in well-defined scenarios, relying o...
Conference Paper
Full-text available
Explainable AI (XAI) has emerged in recent years as a set of techniques and methodologies to interpret and explain machine learning(ML) predictors. To date, many initiatives have been proposed. Nevertheless, current research efforts mainly focus on methods tailored to specific ML tasks and algorithms, such as image classification and sentiment anal...
Chapter
The ability to lazily manipulate long or infinite streams of data is an essential feature in the era of data-driven artificial intelligence. Yet, logic programming technologies currently fall short when it comes to handling long or infinite streams of data. In this paper, we discuss how Prolog can be reinterpreted as a stream processing tool, and r...
Article
Full-text available
Precisely when the success of artificial intelligence (AI) sub-symbolic techniques makes them be identified with the whole AI by many non-computer-scientists and non-technical media, symbolic approaches are getting more and more attention as those that could make AI amenable to human understanding. Given the recurring cycles in the AI history, we e...
Conference Paper
Service self-composition is a well-understood research area focusing on service-based applications providing new services by automatically combining pre-existing ones. In this paper we focus on tuple-based coordination, and propose a solution leveraging logic tuples and tuple spaces to support semantic self-composition for services. A full-stack de...
Article
Full-text available
The blockchain concept and technology are impacting many different research and application fields; hence, many are looking at the blockchain as a chance to solve long-standing problems or gain novel benefits. In the agent community several authors are proposing their own combination of agent-oriented technology and blockchain to address both old a...
Preprint
Service self-composition is a well-understood research area focusing on service-based applications providing new services by automatically combining pre-existing ones. In this paper we focus on tuple-based coordination, and propose a solution leveraging logic tuples and tuple spaces to support semantic self-composition for services. A full-stack de...
Preprint
Mainstream programming languages nowadays tends to be more and more multi-paradigm ones, by integrating diverse programming paradigms-e.g., object-oriented programming (OOP) and functional programming (FP). Logic-programming (LP) is a successful paradigm that has contributed to many relevant results in the areas of symbolic AI and multi-agent syste...
Preprint
The idea of integrating symbolic and sub-symbolic approaches to make intelligent systems (IS) understandable and explainable is at the core of new fields such as neuro-symbolic computing (NSC). This work lays under the umbrella of NSC, and aims at a twofold objective. First, we present a set of guidelines aimed at building explainable IS, which lev...
Article
The more intelligent systems based on sub-symbolic techniques pervade our everyday lives, the less human can understand them. This is why symbolic approaches are getting more and more attention in the general effort to make AI interpretable, explainable, and trustable. Understanding the current state of the art of AI techniques integrating symbolic...
Chapter
Full-text available
Recently, the eXplainable AI (XAI) research community has focused on developing methods making Machine Learning (ML) predictors more interpretable and explainable. Unfortunately, researchers are struggling to converge towards an unambiguous definition of notions such as interpretation, or, explanation—which are often (and mistakenly) used interchan...
Conference Paper
Full-text available
Recently, the eXplainable AI (XAI) research community has focused on developing methods making Machine Learning (ML) predictors more interpretable and explainable. Unfortunately, researchers are struggling to converge towards an unambiguous definition of notions such as interpretation, or, explanation-which are often (and mistakenly) used interchan...
Conference Paper
Full-text available
We propose an abstract framework for XAI based on MAS encompassing the main definitions and results from the literature, focussing on the key notions of interpretation and explanation. KEYWORDS XAI; Multi-Agent Systems; Abstract Framework ACM Reference Format:
Article
Full-text available
Together with the disruptive development of modern sub-symbolic approaches to artificial intelligence (AI), symbolic approaches to classical AI are re-gaining momentum, as more and more researchers exploit their potential to make AI more comprehensible, explainable, and therefore trustworthy. Since logic-based approaches lay at the core of symbolic...
Article
Complexity of intra- and inter-systems interactions is steadily increasing in modern application scenarios such as the Internet of Things, therefore coordination technologies are required to take a crucial step forward towards full maturity. In this paper we look back at the history of the COORDINATION conference series with the goal of shedding li...
Article
Full-text available
A common use case for blockchain smart contracts (SC) is that of governing interaction amongst mutually untrusted parties, by automatically enforcing rules for interaction. However, while many contributions in the literature assess SC computational expressiveness, an evaluation of their power in terms of coordination (i.e., governing interaction) i...
Chapter
In this paper we focus on the expressiveness of smart contracts (SC) and its role in blockchain technologies (BCT), by presenting Tenderfone, a prototypical blockchain platform providing SC as pro-active, time-aware, and asynchronous entities.
Conference Paper
Full-text available
In the context of the Internet of Things (IoT), intelligent systems (IS) are increasingly relying on Machine Learning (ML) techniques. Given the opaqueness of most ML techniques, however, humans have to rely on their intuition to fully understand the IS outcomes: helping them is the target of eXplainable Artificial Intelligence (XAI). Current solut...
Chapter
The Intelligent Edge computing paradigm is playing a major role in the design and development of Cyber-Physical and Cloud Systems (CPCS), extending the Cloud and overcoming its limitations so as to better address the issues related with the physical dimension of data—and therefore of the data-aware intelligence (such as context-awareness and real-t...
Chapter
Features of blockchain technology (BCT) such as decentralisation, trust, fault tolerance, and accountability, are of paramount importance for multi-agent systems (MAS). In this paper we argue that a principled approach to MAS-BCT integration cannot overlook the foundational character of agency—that is, autonomy. Accordingly, we present a custom BCT...
Chapter
Many research works apply blockchain technologies to several different application domains ranging from supply chain and logistics to healthcare and real-estate. There, nevertheless, the blockchain performs the same two core tasks: identity management and asset tracking. In this paper we analyse how the blockchain can be exploited beyond these trad...
Conference Paper
Full-text available
Aggregate Computing is a promising paradigm for coordinating large numbers of possibly situated devices, typical of scenarios related to the Internet of Things, smart cities, drone coordination, and mass urban events. Currently, little work has been devoted to study and improve security in aggregate programs, and existing works focus solely on appl...
Article
Full-text available
In this paper we present the ReSpecTX language, toolchain, and standard library as a first step of a path aimed at closing the gap between coordination languages – mostly a prerogative of the academic realm until now – and their industrial counterparts. Since the limited adoption of coordination languages within the industrial realm is also due to...
Article
Full-text available
In the era of Big Data and IoT, successful systems have to be designed to discover, store, process, learn, analyse, and predict from a massive amount of data—in short, they have to behave intelligently. Despite the success of non-symbolic techniques such as deep learning, symbolic approaches to machine intelligence still have a role to play in orde...
Chapter
Full-text available
The lack of a suitable toolchain for programming the interaction space with coordination languages hinders their adoption in the industry, and limits their application as core calculus, proof-of-concept frameworks, or rapid prototyping/simulation environments. In this paper we present the \(\texttt {ReSpecT}\mathbb {X}\) language and toolchain as a...
Conference Paper
Full-text available
We propose a formalisation of spiking neural networks based on timed automata networks. Neurons are modelled as timed automata waiting for inputs on a number of different channels (synapses), for a given amount of time (the accumulation period). When this period is over, the current potential value is computed taking into account the current inputs...

Network

Cited By