Stefano Nichele

Prof. Stefano Nichele


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 March 2024
Verified
Book Chapter
Closed access
PDF file
SJSanyam Jain
Sanyam Jain
ASAarati Shrestha
Aarati Shrestha
SNStefano Nichele
Stefano Nichele

3 February 2022 in The Knowledge Engineering Review
Verified
Journal Article
Closed access
PDF file
GNGiorgia Nadizar
Giorgia Nadizar
Eric MedvetEric Medvet
Eric Medvet
HRHola Huse Ramstad
Hola Huse Ramstad
SNStefano Nichele
Stefano Nichele
FPFelice Andrea Pellegrino
Felice Andrea Pellegrino
MZMarco Zullich
Marco Zullich
Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/or when high expressive power is desirable. Pruning (removing neurons or connections) reduces the complexity of the ANN, thus increasing its energy efficiency, and has been reported to improve the generalization capability, in some cases. In addition, it is well-known that pruning in biological neural networks plays a fundamental role in the development of brains and their ability to learn. In this study, we consider the evolutionary optimization of neural controllers for the case study of Voxel-based soft robots, a kind of modular, bio-inspired soft robots, applying pruning during fitness evaluation. For a locomotion task, and for centralized as well as distributed controllers, we experimentally characterize the effect of different forms of pruning on after-pruning effectiveness, life-long effectiveness, adaptability to new terrains, and behavior. We find that incorporating some forms of pruning in neuroevolution leads to almost equally effective controllers as those evolved without pruning, with the benefit of higher robustness to pruning. We also observe occasional improvements in generalization ability.

12 July 2023
Verified
Conference Paper
Open access
APAlessandro Pierro
Alessandro Pierro
KHKristine Heiney
Kristine Heiney
SSShamit Shrivastava
Shamit Shrivastava
GMGiulia Marcucci
Giulia Marcucci
SNStefano Nichele
Stefano Nichele
As demand for computational resources reaches unprecedented levels, research is expanding into the use of complex material substrates for computing. In this study, we interface with a model of a hydrodynamic system, under development by a startup, as a computational reservoir and optimize its properties using an evolution in materio approach. Input data are encoded as waves applied to our shallow water reservoir, and the readout wave height is obtained at a fixed detection point. We optimized the readout times and how inputs are mapped to the wave amplitude or frequency using an evolutionary search algorithm, with the objective of maximizing the system's ability to linearly separate observations in the training data by maximizing the readout matrix determinant. Applying evolutionary methods to this reservoir system substantially improved separability on an XNOR task, in comparison to implementations with hand-selected parameters. We also applied our approach to a regression task and show that our approach improves out-of-sample accuracy. Results from this study will inform how we interface with the physical reservoir in future work, and we will use these methods to continue to optimize other aspects of the physical implementation of this system as a computational reservoir.1

14 July 2024
Verified
Conference Paper
Open access
GPGloria Pietropolli
Gloria Pietropolli
SNStefano Nichele
Stefano Nichele
Eric MedvetEric Medvet
Eric Medvet
Cellular automata (CA) are a convenient way to describe the distributed evolution of a dynamical system over discrete time and space. They can be used to express evolutionary algorithms (EAs), where the time is the flow of iterations and the space is where the population is hosted. When the CA evolves over a finite grid of cells, the substrate, each cell hosts an individual and the CA rule applies variation operators using the local and neighbor individuals. In this paper, we explore the possibility of enforcing a structure on the substrate. Instead of a flat toroidal grid, we use substrates where some empty cells never host individuals. These cells may act as barriers, slowing down the propagation of genetic traits and hence potentially improving the population diversity, eventually mitigating the risk of premature convergence. We experimentally evaluate the impact of these substrates using a simple CA-based EA on multi-modal and multi-objective problems. We find evidence of a positive impact in some circumstances; on multi-modal problems, convergence is slightly faster and the EA more often reaches all the targets.

9 October 2018
Verified
Conference Paper
Open access
PDF file
BGBartosz Gembala
Bartosz Gembala
AYAnis Yazidi
Anis Yazidi
HHHårek Haugerud
Hårek Haugerud
SNStefano Nichele
Stefano Nichele

26 April 2022 in The Knowledge Engineering Review
Verified
Journal Article
Closed access
PDF file
GNGiorgia Nadizar
Giorgia Nadizar
Eric MedvetEric Medvet
Eric Medvet
OROla Huse Ramstad
Ola Huse Ramstad
SNStefano Nichele
Stefano Nichele
FPFelice Andrea Pellegrino
Felice Andrea Pellegrino
MZMarco Zullich
Marco Zullich