Search Results for author:
Found 3 papers, 0 papers with code
A simple connection from loss flatness to compressed representations in neural networks
The generalization capacity of deep neural networks has been studied in a variety of ways, including at least two distinct categories of approach: one based on the shape of the loss landscape in parameter space, and the other based on the structure of the representation manifold in feature space (that is, in the space of unit activities).
Recurrent neural networks learn robust representations by dynamically balancing compression and expansion
What determines the dimensionality of activity in neural circuits?
Dimensionality compression and expansion in Deep Neural Networks
Datasets such as images, text, or movies are embedded in high-dimensional spaces.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
