Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 563 for “"Autoencoders"”.

  1. Quantum autoencoders for anomaly detection /

    This thesis investigates quantum autoencoders for anomaly detection under strong dimension‐ ality constraints. We show that simple QAE architectures suffer from overfitting and poor class sep‐ arability when aggressive compression is applied, leading to elevated false‐positive rates (FPR). To …

    vilnius Repository record for Quantum autoencoders for anomaly detection / (opens in a new tab)

  2. Unsupervised Representation Learning with Autoencoders

    … of learning unsupervised representations using autoencoders, and propose regularization techniques that enable autoencoders to learn useful representations of data in unsupervised and semi-supervised settings. First, we exploit sparsity as a generic prior on the representations of autoencoders …

    toronto-retro Repository record for Unsupervised Representation Learning with Autoencoders (opens in a new tab)

  3. Approximate Inference in Variational Autoencoders

    … standard interpretation of importance-weighted autoencoders is that they maximize a tighter lower bound on the marginal likelihood than the standard evidence lower bound. The first contribution of this thesis is to provide an alternative interpretation: that it optimizes the standard variational …

    toronto-retro Repository record for Approximate Inference in Variational Autoencoders (opens in a new tab)

  4. Unsupervised Transfer Learning with Autoencoders

    … used as a datapoint for a computer vision task. Autoencoders are a class of unsupervised learning models. Autoencoders trained on image reconstruction can be fine-tuned on a target task such as image classifcation and semantic segmentation to perform unsupervised transfer learning. This thesis …

    rit Repository record for Unsupervised Transfer Learning with Autoencoders (opens in a new tab)

  5. Representation Learning with Adversarial Latent Autoencoders

    A large number of deep learning methods applied to computer vision problems require encoder-decoder maps. These methods include, but are not limited to, self-representation learning, generalization, few-shot learning, and novelty detection. Encoder-decoder maps are also useful for photo …

    wvu Repository record for Representation Learning with Adversarial Latent Autoencoders (opens in a new tab)

  6. Joint Data Modeling Using Variational Autoencoders

    … recent developments in identifiable variational autoencoders (VAEs), I propose a new joint analysis method, the product of identifiable sufficient experts (POISE-VAE), which posits a latent representation unique to each modality, with latent spaces interacting via an undirected graphical model. …

    duke Repository record for Joint Data Modeling Using Variational Autoencoders (opens in a new tab)

  7. The Polarised Regime of Variational Autoencoders

    Variational Autoencoders ( VAEs ) learn in a polarised regime, a sparsity-enforcing regime where a subset of latent representations (the active variables) are used for reconstruction while the others (the passive variables) are ignored by the decoder. While this regime is well-studied for …

    kent Download PDF for The Polarised Regime of Variational Autoencoders (opens in a new tab)

  8. Hierarchical Bayesian Data Fusion Using Autoencoders

    In this thesis, a novel method for tracker fusion is proposed and evaluated for vision-based tracking. This work combines three distinct popular techniques into a recursive Bayesian estimation algorithm. First, semi supervised learning approaches are used to partition data and to train a deep …

    marquette Repository record for Hierarchical Bayesian Data Fusion Using Autoencoders (opens in a new tab)

  9. Denoising face images using convolutional autoencoders

    In this work, we articially introduce three types of noise (additive gaussian noise, multiplicative noise and salt and-pepper noise) to black-and-white images of human faces and then try to remove the noise by using a specic type of neural network architecture known as an autoencoder. To boost the …

    brazil-uerj Repository record for Denoising face images using convolutional autoencoders (opens in a new tab)

  10. Understanding Variational Autoencoders and Disentanglement Metrics

    … we conduct a thorough study of "Variational Autoencoders". We explain the limitations of ``supervised learning" and emphasize the need for ``generative models" to solve complex problems. Variational Autoencoder (VAE) is an effective tool for generative modeling. We understand the rich …

    washington Repository record for Understanding Variational Autoencoders and Disentanglement Metrics (opens in a new tab)

  11. Imputing metabolomics with graph denoising autoencoders

    The student, Kowshika Sarker, accepted the attached license on 2024-12-06 at 19:10.

    uiuc Repository record for Imputing metabolomics with graph denoising autoencoders (opens in a new tab)

  12. Clustering Mass Spectrometry Data Using Variational Autoencoders

    Mass spectrometry is an analysis technique used to investigate the molecular profile of both biological and non-biological samples. Mass spectrometry imaging (MSI) allows for the spatial mapping of these molecules directly from a physical sample. Clinical applications of MSI are limited, in part …

    queens Repository record for Clustering Mass Spectrometry Data Using Variational Autoencoders (opens in a new tab)

  13. Variational Autoencoders for Clustering Nonlinear Dynamical Trajectories

    … work, we explored the application of Variational Autoencoders (VAEs) and its variants to the task of clustering nonlinear dynamical trajectories. VAEs are powerful neural network capable of learning rich representations of high-dimensional while simultaneously capturing underlying structures. By …

    buffalo Repository record for Variational Autoencoders for Clustering Nonlinear Dynamical Trajectories (opens in a new tab)

  14. When autoencoders meet recommender systems : COFILS approach

    Collaborative Filtering to Supervised Learning (COFILS) transforms a Collaborative Filtering (CF) problem into classical Supervised Learning (SL) problem. Applying COFILS reduce data sparsity and make it possible to test a variety of SL algorithms rather than matrix decomposition methods. It main …

    brazil-uerj Repository record for When autoencoders meet recommender systems : COFILS approach (opens in a new tab)

  15. Visual Co-occurence Learning using Denoising Autoencoders

    Modern recommendation systems are leveraging the recent advances in deep neural networks to provide better recommendations. In addition to making accurate recommendations to users, we are interested in the recommendation of items that are complementary to a set of other items. More specifically, …

    concordia Download PDF for Visual Co-occurence Learning using Denoising Autoencoders (opens in a new tab)

Page 1 of 29