Search Results for author:
Found 14 papers, 7 papers with code
Mapping of attention mechanisms to a generalized Potts model
In MLM, a word is randomly masked in an input sequence, and the network is trained to predict the missing word.
Optimal transfer protocol by incremental layer defrosting
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.
Intrinsic dimension estimation for discrete metrics
Real world-datasets characterized by discrete features are ubiquitous: from categorical surveys to clinical questionnaires, from unweighted networks to DNA sequences.
Prune and distill: similar reformatting of image information along rat visual cortex and deep neural networks
Visual object recognition has been extensively studied in both neuroscience and computer vision.
DADApy: Distance-based Analysis of DAta-manifolds in Python
DADApy is a python software package for analysing and characterising high-dimensional data manifolds.
Redundant representations help generalization in wide neural networks
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.
Ranking the information content of distance measures
Real-world data typically contain a large number of features that are often heterogeneous in nature, relevance, and also units of measure.
Statistically Unbiased Free Energy Estimates from Biased Simulations
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
Dynamical Landscape and Multistability of a Climate Model
We apply two independent data analysis methodologies to locate stable climate states in an intermediate complexity climate model and analyze their interplay.
Hierarchical nucleation in deep neural networks
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.
Intrinsic dimension of data representations in deep neural networks
We find that, in a trained network, the ID is orders of magnitude smaller than the number of units in each layer.
Data segmentation based on the local intrinsic dimension
Here we develop a robust approach to discriminate regions with different local IDs and segment the points accordingly.
Estimating the intrinsic dimension of datasets by a minimal neighborhood information
Analyzing large volumes of high-dimensional data is an issue of fundamental importance in data science, molecular simulations and beyond.
Automatic topography of high-dimensional data sets by non-parametric Density Peak clustering
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.
