Different views of interpretability

B Iooss, R Kenett, P Secchi - Interpretability for Industry 4.0: Statistical and …, 2022 - Springer
Interpretability, in the context of machine learning, means understanding the predictions
made by the machine learning algorithm, with the aim to support human decisions based on …

Mean dimension of generative models for protein sequences

C Feinauer, E Borgonovo - bioRxiv, 2022 - biorxiv.org
Generative models for protein sequences are important for protein design, mutational effect
prediction and structure prediction. In all of these tasks, the introduction of models which …

The twin peaks of learning neural networks

E Demyanenko, C Feinauer… - Machine Learning …, 2024 - iopscience.iop.org
Recent works demonstrated the existence of a double-descent phenomenon for the
generalization error of neural networks, where highly overparameterized models escape …