Search Results for author:
Found 15 papers, 9 papers with code
A Character-Word Compositional Neural Language Model for Finnish
Inspired by recent research, we explore ways to model the highly morphological Finnish language at the level of characters while maintaining the performance of word-level models.
Semi-Supervised Domain Adaptation for Weakly Labeled Semantic Video Object Segmentation
We propose a semi-supervised approach to adapting CNN image recognition model trained from labeled image data to the target domain exploiting both semantic evidence learned from CNN, and the intrinsic structures of video data.
Ladder Variational Autoencoders
Variational Autoencoders are powerful models for unsupervised learning.
Bidirectional Recurrent Neural Networks as Generative Models
Although unidirectional RNNs have recently been trained successfully to model such time series, inference in the negative time direction is non-trivial.
Scalable Gradient-Based Tuning of Continuous Regularization Hyperparameters
Hyperparameter selection generally relies on running multiple full training trials, with selection based on validation set performance.
Semi-Supervised Learning with Ladder Networks
We combine supervised learning with unsupervised learning in deep neural networks.
DopeLearning: A Computational Approach to Rap Lyrics Generation
First, we develop a prediction model to identify the next line of existing lyrics from a set of candidate next lines.
Lateral Connections in Denoising Autoencoders Support Supervised Learning
We show how a deep denoising autoencoder with lateral connections can be used as an auxiliary unsupervised learning task to support supervised learning.
Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series
Although unidirectional RNNs have recently been trained successfully to model such time series, inference in the negative time direction is non-trivial.
Denoising autoencoder with modulated lateral connections learns invariant representations of natural images
Suitable lateral connections between encoder and decoder are shown to allow higher layers of a denoising autoencoder (dAE) to focus on invariant representations.
Iterative Neural Autoregressive Distribution Estimator NADE-k
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data.
Ranked #8 on
Image Generation
on Binarized MNIST
Linear State-Space Model with Time-Varying Dynamics
The time dependency is obtained by forming the state dynamics matrix as a time-varying linear combination of a set of matrices.
Techniques for Learning Binary Stochastic Feedforward Neural Networks
Our experiments confirm that training stochastic networks is difficult and show that the proposed two estimators perform favorably among all the five known estimators.
Iterative Neural Autoregressive Distribution Estimator (NADE-k)
Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data.
Ranked #7 on
Image Generation
on Binarized MNIST
Stochastic Gradient Estimate Variance in Contrastive Divergence and Persistent Contrastive Divergence
Contrastive Divergence (CD) and Persistent Contrastive Divergence (PCD) are popular methods for training the weights of Restricted Boltzmann Machines.
