Search Results for author:
Found 8 papers, 1 papers with code
Expressive Power of ReLU and Step Networks under Floating-Point Operations
In this work, we analyze the expressive power of neural networks under a more realistic setup: when we use floating-point numbers and operations.
Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach
By employing the aforementioned framework and the Whitney embedding theorem, we provide an upper bound for the minimum width, given by $\operatorname{max}(2d_x+1, d_y) + \alpha(\sigma)$, where $0 \leq \alpha(\sigma) \leq 2$ represents a constant depending on the activation function.
Minimal Width for Universal Property of Deep RNN
In this study, we prove the universality of deep narrow RNNs and show that the upper bound of the minimum width for universality can be independent of the length of the data.
Universal Approximation Property of Fully Convolutional Neural Networks with Zero Padding
Despite its widespread adoption, our understanding of its universal approximation properties has been limited due to its intricate nature.
Finding the global semantic representation in GAN through Frechet Mean
This semantic basis represents sample-independent meaningful perturbations that change the same semantic attribute of an image on the entire latent space.
Analyzing the Latent Space of GAN through Local Dimension Estimation
In this paper, we approach this problem through a geometric analysis of latent spaces as a manifold.
Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
The global warpage implies that the latent space is not well-aligned globally and therefore the global traversal directions are bound to show limited success on it.
Discond-VAE: Disentangling Continuous Factors from the Discrete
To represent these generative factors of data, we introduce two sets of continuous latent variables, private variable and public variable.
