Search Results for author:
Found 5 papers, 4 papers with code
Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals
Interpretability research aims to bridge the gap between the empirical success and our scientific understanding of the inner workings of large language models (LLMs).
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.
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.
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.
