We present TPO, a type system designed to support the type-based modeling of the architectural structure of agent societies. the basic concepts of TPO are presented. the TPO-typing of the multiagent system model suppo...
详细信息
ISBN:
(数字)9783030974572
ISBN:
(纸本)9783030974572;9783030974565
We present TPO, a type system designed to support the type-based modeling of the architectural structure of agent societies. the basic concepts of TPO are presented. the TPO-typing of the multiagent system model supported by the multiagentprogramming framework JaCaMo is presented to illustrate the scope of application of TPO.
this paper describes our system used in the SemEval-2023 Task 10: Towards Explainable Detection of Online Sexism (Kirk et al., 2023). the harmful effects of sexism on the internet have impacted both men and women, yet...
详细信息
ISBN:
(纸本)9781959429999
this paper describes our system used in the SemEval-2023 Task 10: Towards Explainable Detection of Online Sexism (Kirk et al., 2023). the harmful effects of sexism on the internet have impacted both men and women, yet current research lacks a fine-grained classification of sexist content. the task involves three hierarchical sub-tasks, which we addressed by employing a multitask-learning framework. To further enhance our system's performance, we pre-trained the roberta-large (Liu et al., 2019b) and deberta-v3-large (He et al., 2021) models on two million unlabeled data, resulting in significant improvements on sub-tasks A and C. In addition, the multitask-learning approach boosted the performance of our models on sub-tasks A and B. Our system exhibits promising results in achieving explainable detection of online sexism, attaining a test f1-score of 0.8746 on sub-task A (ranking 1st on the leaderboard), and ranking 5th on sub-tasks B and C.
Deep learning has been increasingly successful in the last few years, but its inherent limitations have recently become more evident, especially with respect to explainability and interpretability. Neural-symbolic app...
详细信息
ISBN:
(纸本)9783031155659;9783031155642
Deep learning has been increasingly successful in the last few years, but its inherent limitations have recently become more evident, especially with respect to explainability and interpretability. Neural-symbolic approaches to inductive logic programming have been recently proposed to synergistically combine the advantages of inductive logic programming in terms of explainability and interpretability withthe characteristic capability of deep learning to treat noisy, erroneous, and non-logical data. this paper surveys and briefly compares four relevant neural-symbolic approaches to inductive logic programmingthat have been proposed in the last five years and that use templates as an effective basis to learn logic programs from data.
Testing undeniably plays a central role in the daily practice of software engineering, and this explains why better and more efficient libraries and services are continuously made available to developers and designers...
详细信息
ISBN:
(数字)9783030974572
ISBN:
(纸本)9783030974572;9783030974565
Testing undeniably plays a central role in the daily practice of software engineering, and this explains why better and more efficient libraries and services are continuously made available to developers and designers. Could the MAS developers community similarly benefit from utilizing state-of-the-art testing approaches? the paper investigates the possibility of bringing modern software testing tools as those used in mainstream software engineering into multi-agentsystems engineering. Our contribution explores and illustrates, by means of a concrete example, the possible interactions between the agent-based programming framework ASC2 (agentScript Cross-Compiler) and various testing approaches (unit/agent testing, integration/system testing, continuous integration) and elaborate on how the design choices of ASC2 enable these interactions.
the proceedings contain 3 papers. the topics discussed include: SABO: dynamic MPI+OpenMP resource balancer;LEC-PR: proactive recovery method in erasure-coded storage;and Petri nets for concurrent programming.
ISBN:
(纸本)9781665475082
the proceedings contain 3 papers. the topics discussed include: SABO: dynamic MPI+OpenMP resource balancer;LEC-PR: proactive recovery method in erasure-coded storage;and Petri nets for concurrent programming.
the proceedings contain 16 papers. the topics discussed include: synthesis of special operating decisions as part of adaptive control of a mobile robot;software implementation of calculation of technical characteristi...
the proceedings contain 16 papers. the topics discussed include: synthesis of special operating decisions as part of adaptive control of a mobile robot;software implementation of calculation of technical characteristics of water treatment systems in power engineering;natural non-group symmetry in modern applications;design of neuro-simulation system in situational management of control and quality assessment for complex production assembly system;prerequisites for the development of digitalization in regional industry;implementation of decision-making algorithms in redundant systems on FPGA;software development based on artificial neural networks for fitness club;and control system for multi-agent groups of heterogeneous sensors.
Two approaches to the calculation of structural management of the technological complex of the economy are considered: consolidated - using the optimizing model of multi-product reproduction and local - using the bala...
详细信息
With active hardware development, the number of software machine learning-based systems has increased dramatically in all areas of human activity, in particular, in medicine. the use of machine learning elements in so...
详细信息
With active hardware development, the number of software machine learning-based systems has increased dramatically in all areas of human activity, in particular, in medicine. the use of machine learning elements in software systems requires the organization of a pipeline process of software development, testing, and support. the application of MLOps technologies will improve the quality and speed of system development, as well as simplify the process of adjusting the algorithm parameters to improve the system operation quality. the purpose of this work is to develop an MLOps pipeline that will consider all the necessary stages of software development based on machine learning algorithms for biomedical image processing.
We propose a distributed framework, driving a team of robots for the sanitization of very large dynamic indoor environment, as the railway station. A centralized server uses the Hierarchical Mixed Integer Linear Progr...
详细信息
We propose a distributed framework, driving a team of robots for the sanitization of very large dynamic indoor environment, as the railway station. A centralized server uses the Hierarchical Mixed Integer Linear programming to coordinate the robots assigning different zones where the cleaning is a priority;thanks to the Model Predictive Control approach we use historical data about the distribution of people and the knowledge about the transportation service of the station, to predict the future dynamic evolution of the position of people in the environment and the spreading of the contaminants. Each robot navigates the large environment represented as a gridmap, exploiting the Artificial Potential Fields technique in order to reach and clean the assigned areas. We tested our solution considering real data collected by the WiFi network of the main Italian railway station, Roma Termini. We compared our results with a Decentralized multirobot Deep Reinforcement Learning approach.
Building on prior works on explanation negotiation protocols, this paper proposes a general-purpose protocol for multi-agentsystems where recommender agents may need to provide explanations for their recommendations....
详细信息
暂无评论