Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Neural collapse in the orthoplex regime
James Alcala, Rayna Andreeva, Vladimir A. Kobzar +4
When training a neural network for classification, the feature vectors of the training set are known to collapse to the vertices of a regular simplex, provided the dimension of…
cs.LG2024
On the limits of neural network explainability via descrambling
Shashank Sule, Richard G. Spencer, Wojciech Czaja
We characterize the exact solutions to neural network descrambling--a mathematical model for explaining the fully connected layers of trained neural networks (NNs). By reformulatin…