Search Results for author:
Found 4 papers, 4 papers with code
Feature Space Saturation during Training
First, we show that a layer's output can be restricted to the eigenspace of its variance matrix without performance loss.
Perceiving Music Quality with GANs
By using the human rated dataset we show that the discriminator score correlates significantly with the subjective ratings, suggesting that the proposed method can be used to create a no-reference musical audio quality assessment measure.
Spectral Analysis of Latent Representations
We propose a metric, Layer Saturation, defined as the proportion of the number of eigenvalues needed to explain 99% of the variance of the latent representations, for analyzing the learned representations of neural network layers.
Software Engineering Challenges of Deep Learning
A set of seven projects have been selected to describe the potential with this new technology and to identify associated main challenges.
