Search Results for author:
Found 20 papers, 8 papers with code
Generalized Denoising Auto-Encoders as Generative Models
Recent work has shown how denoising and contractive autoencoders implicitly capture the structure of the data-generating density, in the case where the corruption noise is Gaussian, the reconstruction error is the squared error, and the data is continuous-valued.
Bounding the Test Log-Likelihood of Generative Models
Several interesting generative learning algorithms involve a complex probability distribution over many random variables, involving intractable normalization constants or latent variable normalization.
Multimodal Transitions for Generative Stochastic Networks
Generative Stochastic Networks (GSNs) have been recently introduced as an alternative to traditional probabilistic modeling: instead of parametrizing the data distribution directly, one parametrizes a transition operator for a Markov chain whose stationary distribution is an estimator of the data generating distribution.
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
On the Equivalence Between Deep NADE and Generative Stochastic Networks
Orderless NADEs are trained based on a criterion that stochastically maximizes $P(\mathbf{x})$ with all possible orders of factorizations.
Describing Videos by Exploiting Temporal Structure
In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions.
GSNs : Generative Stochastic Networks
We introduce a novel training principle for probabilistic models that is an alternative to maximum likelihood.
Oracle performance for visual captioning
The task of associating images and videos with a natural language description has attracted a great amount of attention recently.
Delving Deeper into Convolutional Networks for Learning Video Representations
We propose an approach to learn spatio-temporal features in videos from intermediate visual representations we call "percepts" using Gated-Recurrent-Unit Recurrent Networks (GRUs). Our method relies on percepts that are extracted from all level of a deep convolutional network trained on the large ImageNet dataset.
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Learning to diagnose from scratch by exploiting dependencies among labels
The field of medical diagnostics contains a wealth of challenges which closely resemble classical machine learning problems; practical constraints, however, complicate the translation of these endpoints naively into classical architectures.
Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
Diagnostic imaging often requires the simultaneous identification of a multitude of findings of varied size and appearance.
Efficient and Accurate Abnormality Mining from Radiology Reports with Customized False Positive Reduction
Obtaining datasets labeled to facilitate model development is a challenge for most machine learning tasks.
A Strong Baseline for Domain Adaptation and Generalization in Medical Imaging
This work provides a strong baseline for the problem of multi-source multi-target domain adaptation and generalization in medical imaging.
Caveats in Generating Medical Imaging Labels from Radiology Reports
Acquiring high-quality annotations in medical imaging is usually a costly process.
Learning to estimate label uncertainty for automatic radiology report parsing
Bootstrapping labels from radiology reports has become the scalable alternative to provide inexpensive ground truth for medical imaging.
On the diminishing return of labeling clinical reports
Ample evidence suggests that better machine learning models may be steadily obtained by training on increasingly larger datasets on natural language processing (NLP) problems from non-medical domains.
IBEX: An open and extensible method for high content multiplex imaging of diverse tissues
We recently developed Iterative Bleaching Extends multi-pleXity (IBEX), an iterative immunolabeling and chemical bleaching method that enables multiplexed imaging (>65 parameters) in diverse tissues, including human organs relevant for international consortia efforts.
More than Correlation: Do Large Language Models Learn Causal Representations of Space?
Recent work found high mutual information between the learned representations of large language models (LLMs) and the geospatial property of its input, hinting an emergent internal model of space.
Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser
To address these problems, a Disentangled Diffusion-based 3D Human Pose Estimation method with Hierarchical Spatial and Temporal Denoiser is proposed, termed DDHPose.
