Gabriele Di Bari

• PhD in Computer Science
• University of Florence

This paper introduces MADEB, a Memetic Algebraic Differential Evolution algorithm for the Binary search space. MADEB has been applied to the Multidimensional Two-Way Number Partitioning Problem (MDTWNPP) and its main components are the binary differential mutation operator and a variable neighborhood descent procedure. The binary differential mutat...

In this paper, a Neural Networks optimizer based on Self-adaptive Differential Evolution is presented. This optimizer applies mutation and crossover operators in a new way, taking into account the structure of the network according to a per layer strategy. Moreover, a new crossover called interm is proposed, and a new self-adaptive version of DE ca...

Generative Adversarial Network (GAN) is a generative model proposed to imitate real data distributions. The original GAN algorithm has been found to be able to achieve excellent results for the image generation task, but it suffers from problems such as instability and mode collapse. To tackle these problems, many variants of the original model hav...

In this article, we propose a novel and effective evolutionary algorithm for the challenging combinatorial optimization problem known as Multidimensional Two-Way Number Partitioning Problem (MDTWNPP). Since the MDTWNPP has been proven to be NP-hard, in the recent years, it has been been increasingly addressed by means of meta-heuristic approaches....

Neuroevolution is a branch of artificial intelligence that uses evolutionary algorithms to optimize neural networks. During the last thirty years, many evolutionary algorithms have been proposed, someones focused on the neural networks' weights optimization, and others on its structure optimization. The goal of this thesis is to propose new evoluti...

Recent studies have shown that Deep Leaning models are susceptible to adversarial examples, which are data, in general images, intentionally modified to fool a machine learning classifier. In this paper, we present a multi-objective nested evolutionary algorithm to generate universal unrestricted adversarial examples in a black-box scenario. The un...

Recent studies have shown that Deep Leaning models are susceptible to adversarial examples, which are data, in general images, intentionally modified to fool a machine learning classifier. In this paper, we present a multi-objective nested evolutionary algorithm to generate universal unrestricted adversarial examples in a black-box scenario. The un...

Crossover operators are very important components in Evolutionary Computation. Here we are interested in crossovers for the permutation representation that find applications in combinatorial optimization problems such as the permutation flowshop scheduling and the travel-ing salesman problem. We introduce three families of permutation crossovers ba...

Differential Evolution for Neural Networks (DENN) is an optimizer for neural network weights based on Differential Evolution. Although DENN has shown good performance with middle-size networks, the number of weights is an evident limitation of the approach. The aim of this work is to figure out if coevolutionary strategies implemented on top of DEN...

In this report we describe the hate speech detection system for the Italian language developed by a joint team of researchers from the two universities of Perugia (University for Foreigners of Perugia and University of Perugia). The experimental results obtained in the HaSpeeDe task of the Evalita 2018 evaluation campaign are analyzed. Finally, a s...

Recently a research trend of learning algorithms by means of deep learning techniques has started. Most of these are different implementations of the controller-interface abstraction: they use a neural controller as a “processor" and provide different interfaces for input, output and memory management. In this trend, we consider of particular inter...

The target of my research program is to find new approaches to train Neural Networks (NN), in particular using Evolutionary Algorithms (EA). This area of research, called Neuroevolution, studies the optimization of topology and weights of neural networks. The EAs are meta-algorithms, which have many advantages with respect to classical optimization...

In this paper we present an algorithm that optimizes artificial neural networks using Differential Evolution. The evolutionary algorithm is applied according the conventional neuroevolution approach, i.e. to evolve the network weights instead of backpropagation or other optimization methods based on backpropagation. A batch system, similar to that...

EVALITA is a periodic evaluation campaign of Natural Language Processing (NLP) and speech tools for the Italian language. The general objective of EVALITA is to promote the development of language and speech technologies for the Italian language, providing a shared framework where different systems and approaches can be evaluated in a consistent ma...