no code implementations • 30 Nov 2022 • Ciro Antonio Mami, Andrea Coser, Eric Medvet, Alexander T. P. Boudewijn, Marco Volpe, Michael Whitworth, Borut Svara, Gabriele Sgroi, Daniele Panfilo, Sebastiano Saccani
Synthetic data generation has recently gained widespread attention as a more reliable alternative to traditional data anonymization.
2 code implementations • 13 Apr 2022 • Federico Pigozzi, Yujin Tang, Eric Medvet, David Ha
We show experimentally that the evolved robots are effective in the task of locomotion: thanks to self-attention, instances of the same controller embodied in the same robot can focus on different inputs.
no code implementations • 5 Apr 2022 • Marco Virgolin, Eric Medvet, Tanja Alderliesten, Peter A. N. Bosman
Interpretability can be critical for the safe and responsible use of machine learning models in high-stakes applications.
1 code implementation • 5 Apr 2022 • Giorgia Nadizar, Eric Medvet, Stefano Nichele, Sidney Pontes-Filho
Voxel-based Soft Robots (VSRs) are a form of modular soft robots, composed of several deformable cubes, i. e., voxels.
1 code implementation • 13 Apr 2021 • Marco Virgolin, Andrea De Lorenzo, Francesca Randone, Eric Medvet, Mattias Wahde
The latter is estimated by a neural network that is trained concurrently to the evolution using the feedback of the user, which is collected using uncertainty-based active learning.
3 code implementations • 23 Apr 2020 • Marco Virgolin, Andrea De Lorenzo, Eric Medvet, Francesca Randone
We show that it is instead possible to take a meta-learning approach: an ML model of non-trivial Proxies of Human Interpretability (PHIs) can be learned from human feedback, then this model can be incorporated within an ML training process to directly optimize for interpretability.
2 code implementations • 23 Jan 2020 • Eric Medvet, Alberto Bartoli, Andrea De Lorenzo, Stefano Seriani
Voxel-based soft robots (VSRs) are aggregations of soft blocks whose design is amenable to optimization.
no code implementations • 6 Dec 2018 • Eric Medvet, Alberto Bartoli, Alessio Ansuini, Fabiano Tarlao
We explore the use of Intrinsic Dimension (ID) for gaining insights in how populations evolve in Evolutionary Algorithms.