1 code implementation • 12 May 2025 • Jian Liu, Xiongtao Shi, Thai Duy Nguyen, Haitian Zhang, Tianxiang Zhang, Wei Sun, YanJie Li, Athanasios V. Vasilakos, Giovanni Iacca, Arshad Ali Khan, Arvind Kumar, Jae Won Cho, Ajmal Mian, Lihua Xie, Erik Cambria, Lin Wang
The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments.
1 code implementation • 7 May 2025 • Zinan Liu, Haoran Li, Jingyi Lu, Gaoyuan Ma, Xu Hong, Giovanni Iacca, Arvind Kumar, Shaojun Tang, Lin Wang
In this work, we propose a novel neuroscience-inspired framework for agentic reasoning.
no code implementations • 16 Apr 2025 • Stefano Genetti, Alberto Longobardi, Giovanni Iacca
To overcome this issue, in this work, we employ an Interpretable Artificial Intelligence (IAI) approach that combines evolutionary computation with Reinforcement Learning (RL) to generate interpretable decision-making policies in the form of decision trees.
1 code implementation • CVPR 2025 • Matteo Farina, Massimiliano Mancini, Giovanni Iacca, Elisa Ricci
An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop.
1 code implementation • 29 Jan 2025 • Fabrizio Sandri, Elia Cunegatti, Giovanni Iacca
The second stage (Depth Pruning), instead, removes entire Attention submodules.
1 code implementation • 17 Dec 2024 • Mátyás Vincze, Laura Ferrarotti, Leonardo Lucio Custode, Bruno Lepri, Giovanni Iacca
SMOSE combines a set of interpretable decisionmakers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts.
1 code implementation • 11 Nov 2024 • Elia Cunegatti, Leonardo Lucio Custode, Giovanni Iacca
Hence, we propose \textsc{NeuroAL}, a \emph{top-up} algorithm that can be used on top of any given pruning algorithm for LLMs, which modifies the block-wise and row-wise sparsity exploiting information from both the dense model and its sparse version to maximize the \emph{neuron alignment} among activations.
1 code implementation • 5 Aug 2024 • Leonardo Lucio Custode, Fabio Caraffini, Anil Yaman, Giovanni Iacca
Hyperparameter optimization is a crucial problem in Evolutionary Computation.
1 code implementation • 19 Jul 2024 • Edoardo Barba, Anil Yaman, Giovanni Iacca
In this paper, we define various training schedules to specify how these variations are introduced during an evolutionary learning process.
no code implementations • 12 Jun 2024 • Ryan Zhou, Jaume Bacardit, Alexander Brownlee, Stefano Cagnoni, Martin Fyvie, Giovanni Iacca, John McCall, Niki van Stein, David Walker, Ting Hu
Artificial intelligence methods are being increasingly applied across various domains, but their often opaque nature has raised concerns about accountability and trust.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
1 code implementation • 28 May 2024 • Matteo Farina, Gianni Franchi, Giovanni Iacca, Massimiliano Mancini, Elisa Ricci
Thanks to its simplicity and comparatively negligible computation, ZERO can serve as a strong baseline for future work in this field.
1 code implementation • 16 May 2024 • Stefano Genetti, Eros Ribaga, Elia Cunegatti, Quintino Francesco Lotito, Giovanni Iacca
Among the various methods for solving the IM problem, evolutionary algorithms (EAs) have been shown to be particularly effective.
1 code implementation • CVPR 2024 • Matteo Farina, Massimiliano Mancini, Elia Cunegatti, Gaowen Liu, Giovanni Iacca, Elisa Ricci
In this challenging setting, the transferable representations already encoded in the pretrained model are a key aspect to preserve.
1 code implementation • 27 Mar 2024 • Elia Cunegatti, Leonardo Lucio Custode, Giovanni Iacca
The Influence Maximization (IM) problem seeks to discover the set of nodes in a graph that can spread the information propagation at most.
1 code implementation • 16 Feb 2024 • Andrea Ferigo, Elia Cunegatti, Giovanni Iacca
To overcome this limitation, we propose a novel plasticity model, called Neuron-centric Hebbian Learning (NcHL), where optimization focuses on neuron- rather than synaptic-specific Hebbian parameters.
no code implementations • 27 Jan 2024 • Leonardo Lucio Custode, Giovanni Iacca
(2) In the individual phase, then, each agent refines its individual performance by interacting with its own instance of the environment.
1 code implementation • 26 May 2023 • Elia Cunegatti, Matteo Farina, Doina Bucur, Giovanni Iacca
With these novelties, we show the following: (a) The proposed MGE allows to extract topological metrics that are much better predictors of the accuracy drop than metrics computed from current input-agnostic BGEs; (b) Which metrics are important at different sparsity levels and for different architectures; (c) A mixture of our topological metrics can rank PaI algorithms more effectively than Ramanujan-based metrics.
1 code implementation • 3 Apr 2023 • Andrea Ferigo, Giovanni Iacca
We compare our proposed SBNN with traditional neural networks (NNs) over three classical control tasks from OpenAI.
no code implementations • 17 Aug 2022 • Andrea Ferigo, Leonardo Lucio Custode, Giovanni Iacca
Addressing the need for explainable Machine Learning has emerged as one of the most important research directions in modern Artificial Intelligence (AI).
no code implementations • 10 Aug 2022 • Anil Yaman, Joel Z. Leibo, Giovanni Iacca, Sang Wan Lee
Here we show that by introducing a model of social norms, which we regard as emergent patterns of decentralized social sanctioning, it becomes possible for groups of self-interested individuals to learn a productive division of labor involving all critical roles.
1 code implementation • 24 Jun 2022 • Michele Tessari, Giovanni Iacca
We demonstrate the applicability of this framework on two algorithms, namely Covariance Matrix Adaptation Evolution Strategies (CMA-ES) and Differential Evolution (DE), for which we learn, respectively, adaptation policies for the step-size (for CMA-ES), and the scale factor and crossover rate (for DE).
no code implementations • 27 Apr 2022 • Anil Yaman, Tim Van der Lee, Giovanni Iacca
With the advent of cheap, miniaturized electronics, ubiquitous networking has reached an unprecedented level of complexity, scale and heterogeneity, becoming the core of several modern applications such as smart industry, smart buildings and smart cities.
1 code implementation • 13 Apr 2022 • Elia Cunegatti, Giovanni Iacca, Doina Bucur
Finding the most influential nodes in a network is a computationally hard problem with several possible applications in various kinds of network-based problems.
no code implementations • 8 Apr 2022 • Leonardo Lucio Custode, Giovanni Iacca
For this reason, several works have applied machine learning techniques, often with the help of special-purpose simulators, to generate policies that were more effective than the ones obtained by governments.
no code implementations • 10 Feb 2022 • Leonardo Lucio Custode, Giovanni Iacca
However, they struggle when working with raw data, especially when the input dimensionality increases and the raw inputs alone do not give valuable insights on the decision-making process.
1 code implementation • 30 Apr 2021 • Kateryna Konotopska, Giovanni Iacca
Social networks represent nowadays in many contexts the main source of information transmission and the way opinions and actions are influenced.
no code implementations • 30 Apr 2021 • Hao Qiu, Leonardo Lucio Custode, Giovanni Iacca
Several methods able to generate adversarial samples make use of gradients, which usually are not available to an attacker in real-world scenarios.
1 code implementation • 25 Apr 2021 • Enrico Zardini, Davide Zappetti, Davide Zambrano, Giovanni Iacca, Dario Floreano
Designing optimal soft modular robots is difficult, due to non-trivial interactions between morphology and controller.
1 code implementation • 31 Mar 2021 • Quintino Francesco Lotito, Leonardo Lucio Custode, Giovanni Iacca
The evolution of symbolic communication is a longstanding open research question in biology.
no code implementations • 31 Mar 2021 • Ahmed Hallawa, Anil Yaman, Giovanni Iacca, Gerd Ascheid
Notably, the KIEA framework is EA-agnostic (i. e., it works with any evolutionary algorithm), problem-independent (i. e., it is not dedicated to a specific type of problems), expandable (i. e., its knowledge base can grow over time).
1 code implementation • 12 Mar 2021 • Michela Lorandi, Leonardo Lucio Custode, Giovanni Iacca
We apply this methodology, in silico, to six test cases of urban networks made of hundreds of nodes, and find that GI produces consistent gains in delivery probability in four cases.
1 code implementation • 14 Dec 2020 • Leonardo Lucio Custode, Giovanni Iacca
We present a two-level optimization scheme that combines the advantages of evolutionary algorithms with the advantages of Q-learning.
Ranked #1 on
OpenAI Gym
on LunarLander-v2
no code implementations • 9 Jul 2020 • Ahmed Hallawa, Thorsten Born, Anke Schmeink, Guido Dartmann, Arne Peine, Lukas Martin, Giovanni Iacca, A. E. Eiben, Gerd Ascheid
Furthermore, we propose that this distinction is decided by the evolutionary process, thus allowing evo-RL to be adaptive to different environments.
no code implementations • 28 Mar 2020 • Anil Yaman, Giovanni Iacca
In several network problems the optimum behavior of the agents (i. e., the nodes of the network) is not known before deployment.
no code implementations • 10 Feb 2020 • Anil Yaman, Giovanni Iacca, Decebal Constantin Mocanu, George Fletcher, Mykola Pechenizkiy
A learning process with the plasticity property often requires reinforcement signals to guide the process.
no code implementations • 15 May 2019 • Cristiano Saltori, Subhankar Roy, Nicu Sebe, Giovanni Iacca
Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i. e., network architectures) and is therefore memory expensive.
no code implementations • 2 Apr 2019 • Anil Yaman, Giovanni Iacca, Decebal Constantin Mocanu, Matt Coler, George Fletcher, Mykola Pechenizkiy
Hebbian learning is a biologically plausible mechanism for modeling the plasticity property in artificial neural networks (ANNs), based on the local interactions of neurons.
no code implementations • 22 Mar 2019 • Anil Yaman, Giovanni Iacca, Decebal Constantin Mocanu, George Fletcher, Mykola Pechenizkiy
Inspired by biology, plasticity can be modeled in artificial neural networks by using Hebbian learning rules, i. e. rules that update synapses based on the neuron activations and reinforcement signals.
1 code implementation • 2 Feb 2019 • Stefano Fioravanzo, Giovanni Iacca
As such, it could be used in the future as an effective building-block for designing new constrained optimization algorithms.
no code implementations • 11 Oct 2018 • Giovanni Iacca, Fabio Caraffini, Ferrante Neri
We propose Multi-Strategy Coevolving Aging Particles (MS-CAP), a novel population-based algorithm for black-box optimization.
no code implementations • 5 Oct 2018 • Giovanni Iacca
We perform extensive tests of different DOWSN configurations on a benchmark made up of continuous optimization problems; we analyze the influence of the network parameters (number of nodes, inter-node communication period and probability of accepting incoming solutions) on the optimization performance.
no code implementations • 12 Sep 2018 • Giovanni Iacca, Fabio Caraffini
The resulting compact algorithms with RI are tested on the CEC 2014 benchmark functions.
no code implementations • 19 Apr 2018 • Anil Yaman, Decebal Constantin Mocanu, Giovanni Iacca, George Fletcher, Mykola Pechenizkiy
Many real-world control and classification tasks involve a large number of features.