arXiv research

A neural network finds causal relationships among latent variables.

DSVNP uses global and local latent variables for improved neural process predictions.

New method identifies latent variables in cognitive models using neural networks.

In this paper, we propose an interpretable LSTM recurrent neural network, i.e., multi-variable LSTM for time series with exogenous variables. Currently, widely used attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To th…

Hybrid quantum neural networks predict continuous variables.

Electronic Medical Records (EMR) are a rich source of patient information, including measurements reflecting physiologic signs and administered therapies. Identifying which variables are useful in predicting clinical outcomes can be challenging. Advanced algorithms such as deep neural networks were designed to process …

Package provides sensitivity analysis for neural networks.

For recurrent neural networks trained on time series with target and exogenous variables, in addition to accurate prediction, it is also desired to provide interpretable insights into the data. In this paper, we explore the structure of LSTM recurrent neural networks to learn variable-wise hidden states, with the aim t…

The paper shows how neural networks with less decision boundary variability generalize better.

This study compares machine learning methods for high-cardinality categorical variables.

Paper proposes knockoff-based methods to simplify deep neural networks by controlling false discovery rates.

Neural population activity often exhibits rich variability and temporal structure. This variability is thought to arise from single-neuron stochasticity, neural dynamics on short time-scales, as well as from modulations of neural firing properties on long time-scales, often referred to as "non-stationarity". To better …

This work develops rigorous theoretical basis for the fact that deep Bayesian neural network (BNN) is an effective tool for high-dimensional variable selection with rigorous uncertainty quantification. We develop new Bayesian non-parametric theorems to show that a properly configured deep BNN (1) learns the variable im…

In this paper, we propose multi-variable LSTM capable of accurate forecasting and variable importance interpretation for time series with exogenous variables. Current attention mechanism in recurrent neural networks mostly focuses on the temporal aspect of data and falls short of characterizing variable importance. To …

This paper theoretically explains and validates a deep neural network approach to IV estimation.

New model uncovers non-Euclidean neural representations.

Statistical mechanics reveals phase transitions in $\varepsilon$-SVR error.

LAVARNET predicts multivariate time series by estimating causal variable relationships.

pi-VAE models neural activity with interpretable latent variables.

Paper uses neural networks to predict NOx emissions from gas turbines.

VPNet uses variable projection for efficient neural network training.

Fast method estimates variable importance for large neural networks.

The study investigates how data variability impacts the generalization of neural networks.

A neural network approach unifies Lasso for variable selection.

Bayesian neural networks improve uncertainty quantification in non-linear dimensionality reduction.

IANN visualizes all input variables effects simultaneously.

CIPNN model tackles continuous latent variables, solving intractable posterior problems.

Neural networks learn faster with correlated latent variables.

Improved robust latent variable estimation for neural dynamics.

Paper introduces multitask neural networks for efficient stochastic control problems.

FAIR-NN finds invariant variables for causal inference across diverse environments.

Variational autoencoders often collapse, showing latent variables are non-identifiable.

New neural network approach for optimizing latent variable models.

Algorithm learns latent variables for thermodynamically-consistent deep neural networks.

Proposes a neural network framework for feature selection in high-dimensional settings.

Estimates causal effects using neural autoregressive density estimators.

Deep neural networks estimate regression functions on manifolds.

We derive a novel sensitivity analysis of input variables for predictive epistemic and aleatoric uncertainty. We use Bayesian neural networks with latent variables as a model class and illustrate the usefulness of our sensitivity analysis on real-world datasets. Our method increases the interpretability of complex blac…

The architectures of deep neural networks (DNN) rely heavily on the underlying grid structure of variables, for instance, the lattice of pixels in an image. For general high dimensional data with variables not associated with a grid, the multi-layer perceptron and deep belief network are often used. However, it is freq…

Enhances FDR control in variable selection using neural networks.

In genomic analysis, biomarker discovery, image recognition, and other systems involving machine learning, input variables can often be organized into different groups by their source or semantic category. Eliminating some groups of variables can expedite the process of data acquisition and avoid over-fitting. Research…

We develop a pivotal test to assess the statistical significance of the feature variables in a single-layer feedforward neural network regression model. We propose a gradient-based test statistic and study its asymptotics using nonparametric techniques. Under technical conditions, the limiting distribution is given by …

Deep neural networks (DNNs) are famous for their high prediction accuracy, but they are also known for their black-box nature and poor interpretability. We consider the problem of variable selection, that is, selecting the input variables that have significant predictive power on the output, in DNNs. We propose a backw…

Derives PDEs from data using manifold learning and neural networks.

LatentNN corrects neural network attenuation bias in astronomical data.

Method discovers local independence in systems with continuous variables.

New method estimates variable importance for large models efficiently.

We consider the statistical problem of learning common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach is useful in particular in exploratory, data-driven applications, where neither …