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 4 of 4 for “"Conditional autoencoder"”.

  1. Self-supervised learning of structural representations of visual objects

    … object landmarks without any annotations using a conditional autoencoder with 2D keypoint bottleneck that disentangles pose, represented as 2D keypoints, and appearance. Despite the ability of self-supervised learning methods to learn stable object landmarks, the automatically discovered landmarks …

    oxford Repository record for Self-supervised learning of structural representations of visual objects (opens in a new tab)

  2. Interpreting Machine Learning Models using Conditional Counterfactual Generation

    … machine learning models is proposed, where an autoencoder is used to generate reconstructions of data to visualize in an interpretable way what patterns a model has learned to detect. The method is first shown to work for a simple constructed problem, being able to interpret a model that has …

    chalmers Repository record for Interpreting Machine Learning Models using Conditional Counterfactual Generation (opens in a new tab)

  3. DIMENSION REDUCTION INVOLVING EXOGENOUS VARIABLES WITH APPLICATIONS IN MANUFACTURING AND HEALTHCARE

    … By developing a variation model estimated via a conditional autoencoder, the study enables the discovery of unanticipated variation patterns even with limited sample sizes from different designs. This approach successfully reveals critical interactions between latent variation sources and …

    vcu Repository record for DIMENSION REDUCTION INVOLVING EXOGENOUS VARIABLES WITH APPLICATIONS IN MANUFACTURING AND HEALTHCARE (opens in a new tab)

  4. Computational models of multimodal interaction for music generation and music information retrieval

    … deep convolutional architectures incorporating a conditional autoencoder with dilated causal highway gates, outperform recurrent models in generating diverse and realistic dance motion sequences. Next, in the context of jazz improvisation, we focus on simulating the interplay between human …

    greece Repository record for Computational models of multimodal interaction for music generation and music information retrieval (opens in a new tab)