A neural network finds causal relationships among latent variables.
problem Learning causal structure among latent variables in high-dimensional data.
method Redundant Input Neural Network (RINN) with modified architecture and regularized objective function.
result The RINN method successfully recovers latent causal structure between input and output variables.
This paper enhances LSTM neural networks for multi-variable time series data, providing interpretable insights.
problem Accurate prediction of multi-variable time series data with interpretable insights.
method Variable-wise hidden states and a mixture attention mechanism to model the generative process of the target variable.
result Enhanced prediction performance by capturing the dynamics of different variables.
Proposes an interpretable LSTM for time series with exogenous variables.
problem Lack of variable importance characterization in recurrent neural networks.
method Develops a multi-variable LSTM with tensorized hidden states for learning variable-specific representations.
result Variable attention in real datasets is highly aligned with statistical causality.
DSVNP uses global and local latent variables for improved neural process predictions.
problem Limited expressiveness of vanilla neural processes in capturing target-specific local variation.
method Introduces DSVNP combining global and local latent variables for prediction.
result Competitive prediction performance in multi-output regression and uncertainty estimation.
New method identifies latent variables in cognitive models using neural networks.
problem Inference of latent variables in complex cognitive models is limited.
method Recurrent neural networks and simulation-based inference for latent variable sequences.
result Extends neural Bayes estimation to broader classes of cognitive models.
RNN models perform similarly with or without extraneous variables.
problem Impact of extraneous variables on RNN performance in clinical tasks.
method Investigated the effect of extraneous input variables on RNN predictive performance using EMR and randomly drawn variables.
result Degradations in RNN's predictive performance with extraneous variables were negligible.
Deep Bayesian neural networks effectively select variables with rigorous uncertainty quantification.
problem High-dimensional variable selection with uncertainty.
method Developed new Bayesian non-parametric theorems for deep BNNs.
result BNNs can learn variable importance effectively in high dimensions and rigorously quantify uncertainty.
Proposes a multi-variable LSTM for accurate time series forecasting and variable importance.
problem Current attention mechanisms in recurrent neural networks fail to characterize variable importance in time series with exogenous variables.
method Develops a multi-variable LSTM with tensorized hidden states to learn variable importance and a mixture of temporal and variable attention.
result Demonstrates superior prediction performance and variable importance quantification compared to baselines.
End-to-end auto-encoder for neural image compression with variable bit rates.
problem Efficient image compression with variable bit rates.
method Block-based auto-encoder system with novel contributions.
result Incremental performance improvement of each contribution.
Hybrid quantum neural networks predict continuous variables.
problem Predicting continuous variables using quantum computing.
method Quantum classical hybrid neural networks for continuous variable prediction.
result Quantum neural networks outperform classical methods in continuous variable prediction.
Package provides sensitivity analysis for neural networks.
problem Understanding how input variables affect neural network predictions.
method Partial derivatives method to calculate sensitivities.
result Allows evaluation of variable importance and input-output relationships.
New method finds sparse groups of input variables for neural networks.
problem Finding optimal groups of input variables for neural networks.
method Developed a new loss function and optimization algorithm for multi-layer non-linear neural networks to achieve group sparsity.
result Achieved group sparsity in three real-world datasets, improving model performance and excluding a significant number of variables.
The paper shows how neural networks with less decision boundary variability generalize better.
problem Improving neural network generalizability by reducing decision boundary variability.
method Introduces new measures (algorithm DB variability and ( ε , η ) (ε, η) ( ε , η ) -data DB variability) to quantify decision boundary variability and proves theoretical bounds on generalizability. result Neural networks with lower decision boundary variability have better generalizability, as shown by extensive experiments and theoretical bounds.
Proposes DVC for better variable selection in non-grid data.
problem Challenges of identifying important variables in non-grid data.
method Imposes chain structure on blocks of variables using step-wise greedy search.
result Outperforms other generic DNNs and classifiers.
SurvNet selects important variables in DNNs with false discovery rate control.
problem Variable selection in deep neural networks (DNNs) for interpretability.
method Backward elimination procedure based on a new variable importance measure.
result SurvNet estimates and controls false discovery rate of selected variables.
Develops a test to assess feature significance in neural networks.
problem Assessing the statistical significance of feature variables in neural networks.
method Gradient-based test statistic, asymptotic analysis using nonparametric techniques.
result Tests enable ranking variables by their influence on neural network predictions.
Bayesian neural network improves feature selection and prediction.
problem Improving feature selection and prediction accuracy in neural networks.
method BNN-ARD with l2-norm feature importance measure.
result Improves variable selection and predictive performance on real-world data.
This study compares machine learning methods for high-cardinality categorical variables.
problem Machine learning struggles with high-cardinality categorical variables.
method Empirical comparison of tree-boosting, deep neural networks, and linear mixed effects models.
result Tree-boosting with random effects outperforms deep neural networks with random effects.
Paper proposes knockoff-based methods to simplify deep neural networks by controlling false discovery rates.
problem High-dimensional deep neural networks with many irrelevant parameters and inputs.
method Knockoff methods combined with regularized neural networks for variable screening.
result Proposed algorithms show satisfactory performance in controlling false discovery rates.
New BMI decoder robust to future neural variability.
problem Current BMIs become ineffective with changing neural conditions.
method Trained multiplicative recurrent neural network to handle diverse neural conditions and synthetic perturbations.
result Successfully learned and became more robust to various neural-to-kinematic mappings.
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 paper theoretically explains and validates a deep neural network approach to IV estimation.
problem Endogeneity issues in empirical applications, especially in the presence of omitted variables, measurement error, or simultaneous causality.
method A two-stage estimator using deep neural networks in a linear instrumental variables model, with a latent structural assumption on the reduced form equation.
result The second-stage estimator achieves the semiparametric efficiency bound, with a smaller estimation error and requiring weaker conditions on the smoothness of optimal instruments.
New model uncovers non-Euclidean neural representations.
problem Discovering latent neural states in complex, non-Euclidean spaces.
method Manifold GPLVM for identifying latent variables and neural contributions.
result mGPLVM correctly recovers non-Euclidean latent structures in neural data.
Statistical mechanics reveals phase transitions in ε \varepsilon ε -SVR error.
problem Understanding task precision in neural representations with variability.
method Statistical mechanics applied to ε \varepsilon ε -SVR. result Double-descent phenomenon in generalization error due to ε \varepsilon ε . Richer prior for neural networks with correlated weights.
problem Weak priors limit neural network complexity and flexibility.
method Latent variables represent network units, conditional weights.
result Richer meta-representations and representations.
LAVARNET predicts multivariate time series by estimating causal variable relationships.
problem Forecasting multivariate time series requires understanding causal interrelationships among variables.
method LAVARNET is a neural network architecture that estimates causal effects and predicts future values.
result LAVARNET outperforms other models on various real-world data sets.
pi-VAE models neural activity with interpretable latent variables.
problem Difficult interpretation of deep generative models for neural data.
method Adapted variational auto-encoder to integrate task variables.
result Improves interpretability and identifiability of neural codes.
End-to-end speaker recognition method using neural networks.
problem Speaker and session variability in speaker verification.
method Joint Factor Analysis with tied hidden variables, MAP adaptation, two-step backpropagation.
result Improved likelihood ratios and robust performance on RSR2015 database.
Estimates Granger causality with unobserved confounders using deep latent-variable recurrent neural networks.
problem Non-linear Granger causality with unobserved confounders in observational studies.
method Generative model with latent variable, variational autoencoder, recurrent neural network.
result Estimated confounders improve performance in non-linear Granger causality with multiple proxies.
Paper uses neural networks to predict NOx emissions from gas turbines.
problem Predicting NOx emissions from degrading gas turbines.
method Applied neural network algorithm to model NOx emissions from nine process variables.
result Neural network model optimizes process variables for minimal NOx emissions.
VPNet uses variable projection for efficient neural network training.
problem Efficient and interpretable neural network training for signal processing.
method Variable projection (VP) applied to neural networks.
result VPNet achieves fast learning and good accuracy with low computational cost.
Bayesian neural networks decompose uncertainty into epistemic and aleatoric components.
problem Uncertainty in Bayesian neural networks with latent variables.
method Information theoretic approach and risk-sensitive objective for safe reinforcement learning.
result Natural decomposition of predictive uncertainty in Bayesian active learning and safe RL.
Fast method estimates variable importance for large neural networks.
problem Estimating variable importance in large neural networks is computationally expensive and lacks theoretical guarantees.
method Linearization initialized at full model parameters with ridge-like penalty.
result Estimates variable importance with error rate of O ( 1 n ) O(\frac{1}{\sqrt{n}}) O ( n 1 ) and asymptotic normality. The study investigates how data variability impacts the generalization of neural networks.
problem Understanding the impact of data variability on neural network generalization.
method Developed a field-theoretic formalism to compute generalization properties of neural networks, focusing on data variability.
result Data variability leads to non-Gaussian action, affecting the learning curve and generalization properties of neural networks.
Novel sensitivity analysis for neural networks improves model interpretability.
problem Improving interpretability of complex probabilistic models.
method Bayesian neural networks with latent variables and sensitivity analysis.
result Increases interpretability of black-box probabilistic models.
A neural network approach unifies Lasso for variable selection.
problem Combining statistical and machine learning techniques for variable selection.
method Representing Lasso through a neural network and developing a new optimization algorithm.
result The new optimization algorithm achieves better performance than previous methods.
Bayesian neural networks improve uncertainty quantification in non-linear dimensionality reduction.
problem Current neural network models lack adequate uncertainty quantification.
method Deploy Markov chain Monte Carlo sampling algorithms for Bayesian inference in ANN models with latent variables.
result New research directions are needed due to fundamental challenges in neural networks with latent variables.
Neural network identifies undeclared variables and infers their types.
problem Undeclared variable errors in programs.
method Trained on structural semantic details of AST, identifies and infers types of undeclared variables.
result Correctly identified and inferred types for 80% of programs with undeclared variable errors.
IANN visualizes all input variables effects simultaneously.
problem Inability to visualize all input variables effects simultaneously in black-box functions.
method Interpretable Architecture Neural Network (IANN) approach.
result Visualization of all input variables effects directly and simultaneously.
Dual Variable Learning Rates improve neural network training efficiency.
problem Training neural networks efficiently and effectively.
method DVLR uses different learning rates for correct and incorrect responses, and adjusts rates based on network performance.
result DVLR consistently improves neural network accuracy across different types and domains.
CIPNN model tackles continuous latent variables, solving intractable posterior problems.
problem Solving intractable posterior calculation for continuous latent variables.
method Derives analytical solution for posterior of continuous latent variables, proposes CIPNN and CIPAE.
result CIPNN model demonstrates great classification capability, solving problems for continuous latent variables.
Neural networks learn faster with correlated latent variables.
problem Efficiently learning from higher-order correlations in neural networks.
method Analytical derivation and simulations of two-layer neural networks.
result Correlations between latent variables speed up learning from higher-order correlations.
Improved robust latent variable estimation for neural dynamics.
problem Inconsistent results due to noise and nonlinearity in existing models.
method Probabilistic approach to latent variable estimation in decomposed models.
result More accurate latent variable inference in nonlinear systems with diverse noise conditions.
Paper introduces multitask neural networks for efficient stochastic control problems.
problem Infeasibility of simulating state variables in some stochastic control problems.
method Multitask neural networks with dynamic task balancing.
result Multitask neural networks outperform state-of-the-art approaches in derivatives pricing problems.
A new type of neural network variable called 'fast weights' improves sequence models by storing recent past memories.
problem Sequence models benefit from attention to the past, but current neural networks lack a mechanism to store recent past information efficiently.
method Introduce 'fast weights' that change faster than neural activities but slower than standard weights, allowing for temporary memory storage of recent past.
result Fast weights enable efficient implementation of past attention in sequence models without needing to store neural activity patterns.
FAIR-NN finds invariant variables for causal inference across diverse environments.
problem Nonparametric invariance and causal learning in regression models with varying joint distributions.
method FAIR-NN framework using adversarial optimization and neural networks.
result FAIR-NN identifies invariant variables and quasi-causal variables under minimal conditions.
Variational autoencoders often collapse, showing latent variables are non-identifiable.
problem Posterior collapse in variational autoencoders due to non-identifiable latent variables.
method Proves latent variable non-identifiability causes posterior collapse. Proposes latent-identifiable models using Brenier maps and input convex neural networks.
result Latent-identifiable models resolve posterior collapse and provide meaningful representations.
A neural network RG approach for efficient collective variable identification.
problem Identifying mutually independent collective variables in complex systems.
method A variational RG approach using normalizing flows and neural nets to map physical configurations to latent variables with reduced mutual information.
result Direct access to the renormalized energy function of latent variables for unbiased training and efficient sampling.