Data-driven deep density estimation

  title={Data-driven deep density estimation},
  author={Patrik Puchert and Pedro Hermosilla and Tobias Ritschel and Timo Ropinski},
Density estimation plays a crucial role in many data analysis tasks, as it infers a continuous probability density function (PDF) from discrete samples. Thus, it is used in tasks as diverse as analyzing population data, spatial locations in 2D sensor readings, or reconstructing scenes from 3D scans. In this paper, we introduce a learned, data-driven deep density estimation (DDE) to infer PDFs in an accurate and efficient manner, while being independent of domain dimensionality or sample size… Expand


MADE: Masked Autoencoder for Distribution Estimation
This work introduces a simple modification for autoencoder neural networks that yields powerful generative models and proves that this approach is competitive with state-of-the-art tractable distribution estimators. Expand
Adam: A Method for Stochastic Optimization
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Expand
Deep Residual Learning for Image Recognition
This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. Expand
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Expand
Fast on-line kernel density estimation for active object localization
The hypothesis that dynamically-rendered, context-based probabilistic models can support efficient object localization in visual situations can be supported, and a novel method for prior learning and active object localization for this kind of knowledge-driven search in static images is proposed. Expand
Probability density estimation using artificial neural networks
We present an approach for the estimation of probability density functions (pdf) given a set of observations. It is based on the use of feedforward multilayer neural networks with sigmoid hiddenExpand
DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning
Using DeepLesion, a universal lesion detector is trained that can find all types of lesions with one unified framework and achieves a sensitivity of 81.1% with five false positives per image. Expand
Variational inference for Dirichlet process mixtures
Dirichlet process (DP) mixture models are the cornerstone of non- parametric Bayesian statistics, and the development of Monte-Carlo Markov chain (MCMC) sampling methods for DP mixtures has enabledExpand
High throughput nonparametric probability density estimation
Benchmark tests show that estimates for the probability density function (PDF) converge to the true PDF as sample size increases on particularly difficult test probability densities that include cases with discontinuities, multi-resolution scales, heavy tails, and singularities, indicating the method has general applicability for high throughput statistical inference. Expand
A Survey of Deep Learning Techniques: Application in Wind and Solar Energy Resources
Different types of Deep Learning algorithms applied in the field of solar and wind energy resources are discussed and their performance through a novel taxonomy is evaluated and a comprehensive state-of-the-art of the literature is presented leading to an assessment and performance evaluation. Expand