Results 11 to 20 of about 14,221 (268)
CoRR, 2022 Recent progress in Generative Artificial Intelligence (AI) relies on efficient data representations, often featuring encoder-decoder architectures. We formalize the mathematical problem of finding the optimal encoder-decoder pair and characterize its solution, which we name the "benign autoencoder" (BAE). We prove that BAE projects data onto a manifold
Semyon Malamud +4 more
openaire +2 more sources
On the Regularization of Autoencoders
CoRR, 2021 While much work has been devoted to understanding the implicit (and explicit) regularization of deep nonlinear networks in the supervised setting, this paper focuses on unsupervised learning, i.e., autoencoders are trained with the objective of reproducing the output from the input. We extend recent results [Jin et al.
Harald Steck, Dario García-García
openaire +2 more sources
Autoencoding Variational Autoencoder
CoRR, 2020 Neurips ...
A. Taylan Cemgil +4 more
openaire +2 more sources
Autoencoding With a Classifier System [PDF]
IEEE Transactions on Evolutionary Computation, 2021 Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of increasing size comes at the price of additional time and computational cost.
Richard John Preen +2 more
openaire +2 more sources
CoRR, 2020 High dimensional data is often assumed to be concentrated on or near a low-dimensional manifold. Autoencoders (AE) is a popular technique to learn representations of such data by pushing it through a neural network with a low dimension bottleneck while minimizing a reconstruction error.
Matan Atzmon, Amos Gropp, Yaron Lipman
openaire +2 more sources
Journal of Cybersecurity and Privacy, 2023 An intrusion detection system (IDS), whether as a device or software-based agent, plays a significant role in networks and systems security by continuously monitoring traffic behaviour to detect malicious activities.
Fatemeh Ahmadi Abkenari +2 more
doaj +1 more source
CoRR, 2017 In this paper, we describe the "PixelGAN autoencoder", a generative autoencoder in which the generative path is a convolutional autoregressive neural network on pixels (PixelCNN) that is conditioned on a latent code, and the recognition path uses a generative adversarial network (GAN) to impose a prior distribution on the latent code.
Alireza Makhzani, Brendan J. Frey
openaire +3 more sources
Biological Cybernetics, 2022 AbstractIn Bourlard and Kamp (Biol Cybern 59(4):291–294, 1998), it was theoretically proven that autoencoders (AE) with single hidden layer (previously called “auto-associative multilayer perceptrons”) were, in the best case, implementing singular value decomposition (SVD) Golub and Reinsch (Linear algebra, Singular value decomposition and least ...
Hervé Bourlard, Selen Hande Kabil
openaire +3 more sources
CoRR, 2023 The Variational Autoencoder (VAE) is a seminal approach in deep generative modeling with latent variables. Interpreting its reconstruction process as a nonlinear transformation of samples from the latent posterior distribution, we apply the Unscented Transform (UT) -- a well-known distribution approximation used in the Unscented Kalman Filter (UKF ...
Faris Janjos +3 more
openaire +3 more sources