1 code implementation • 18 Feb 2024 • Francesco Ortu, Zhijing Jin, Diego Doimo, Mrinmaya Sachan, Alberto Cazzaniga, Bernhard Schölkopf
Interpretability research aims to bridge the gap between the empirical success and our scientific understanding of the inner workings of large language models (LLMs).
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.
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.
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.