Search Results for author:
Found 6 papers, 4 papers with code
SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization
We propose a novel deep neural network that is both lightweight and effectively structured for model parallelization.
A Hierarchical Latent Structure for Variational Conversation Modeling
To solve the degeneration problem, we propose a novel model named Variational Hierarchical Conversation RNNs (VHCR), involving two key ideas of (1) using a hierarchical structure of latent variables, and (2) exploiting an utterance drop regularization.
Unsupervised Representation Learning via Neural Activation Coding
We argue that the deep encoder should maximize its nonlinear expressivity on the data for downstream predictors to take full advantage of its representation power.
Variational Laplace Autoencoders
Based on the Laplace approximation of the latent variable posterior, VLAEs enhance the expressiveness of the posterior while reducing the amortization error.
Normalized Contrastive Learning for Text-Video Retrieval
Cross-modal contrastive learning has led the recent advances in multimodal retrieval with its simplicity and effectiveness.
Density Uncertainty Layers for Reliable Uncertainty Estimation
In this paper, we propose a novel criterion for reliable predictive uncertainty: a model's predictive variance should be grounded in the empirical density of the input.
