no code implementations • 14 Apr 2023 • Riccardo Rende, Federica Gerace, Alessandro Laio, Sebastian Goldt
In MLM, a word is randomly masked in an input sequence, and the network is trained to predict the missing word.
no code implementations • 2 Mar 2023 • Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio
The simplest transfer learning protocol is based on ``freezing" the feature-extractor layers of a network pre-trained on a data-rich source task, and then adapting only the last layers to a data-poor target task.
no code implementations • 20 Jul 2022 • Iuri Macocco, Aldo Glielmo, Jacopo Grilli, Alessandro Laio
Real world-datasets characterized by discrete features are ubiquitous: from categorical surveys to clinical questionnaires, from unweighted networks to DNA sequences.
no code implementations • 27 May 2022 • Paolo Muratore, Sina Tafazoli, Eugenio Piasini, Alessandro Laio, Davide Zoccolan
Visual object recognition has been extensively studied in both neuroscience and computer vision.
1 code implementation • 4 May 2022 • Aldo Glielmo, Iuri Macocco, Diego Doimo, Matteo Carli, Claudio Zeni, Romina Wild, Maria d'Errico, Alex Rodriguez, Alessandro Laio
DADApy is a python software package for analysing and characterising high-dimensional data manifolds.
1 code implementation • 7 Jun 2021 • Diego Doimo, Aldo Glielmo, Sebastian Goldt, Alessandro Laio
Deep neural networks (DNNs) defy the classical bias-variance trade-off: adding parameters to a DNN that interpolates its training data will typically improve its generalization performance.
no code implementations • 30 Apr 2021 • Aldo Glielmo, Claudio Zeni, Bingqing Cheng, Gabor Csanyi, Alessandro Laio
Real-world data typically contain a large number of features that are often heterogeneous in nature, relevance, and also units of measure.
no code implementations • 11 Feb 2021 • Matteo Carli, Alessandro Laio
Estimating the free energy in molecular simulation requires, implicitly or explicitly, counting how many times the system is observed in a finite region.
Chemical Physics Soft Condensed Matter Computational Physics
no code implementations • 20 Oct 2020 • Georgios Margazoglou, Tobias Grafke, Alessandro Laio, Valerio Lucarini
We apply two independent data analysis methodologies to locate stable climate states in an intermediate complexity climate model and analyze their interplay.
1 code implementation • NeurIPS 2020 • Diego Doimo, Aldo Glielmo, Alessio Ansuini, Alessandro Laio
This process leaves a footprint in the probability density of the output layer where the topography of the peaks allows reconstructing the semantic relationships of the categories.
1 code implementation • NeurIPS 2019 • Alessio Ansuini, Alessandro Laio, Jakob H. Macke, Davide Zoccolan
We find that, in a trained network, the ID is orders of magnitude smaller than the number of units in each layer.
1 code implementation • 27 Feb 2019 • Michele Allegra, Elena Facco, Francesco Denti, Alessandro Laio, Antonietta Mira
Here we develop a robust approach to discriminate regions with different local IDs and segment the points accordingly.
1 code implementation • 19 Mar 2018 • Elena Facco, Maria d'Errico, Alex Rodriguez, Alessandro Laio
Analyzing large volumes of high-dimensional data is an issue of fundamental importance in data science, molecular simulations and beyond.
2 code implementations • 28 Feb 2018 • Maria d'Errico, Elena Facco, Alessandro Laio, Alex Rodriguez
The approach is based on an unsupervised extension of Density Peak clustering and a non-parametric density estimator that measures the probability density in the manifold containing the data.