New method proves neural networks can select features consistently.
problem Feature selection for deep neural networks is challenging.
method Adaptive Group Lasso selection procedure with Group Lasso as the base estimator.
result Adaptive Group Lasso is selection-consistent for a wide class of neural networks.
NGP selects N features from P using neural networks in a greedy, iterative process.
problem Feature selection for non-linear prediction problems.
method Neural Greedy Pursuit (NGP) algorithm, selecting features sequentially in an iterative loss minimization procedure.
result NGP provides better performance than DeepLIFT and Drop-one-out loss methods.
This paper selects features in deep neural networks with theoretical guarantees.
problem Feature selection in deep neural networks with unknown nonlinear functions.
method Reformulate neural networks as index models, estimate feature sets using Stein's formula, and apply screening-and-selection mechanism.
result Consistent feature selection with theoretical guarantees, even in high-dimensional settings.
Adaptive Group Lasso selects important features in neural networks.
problem Lack of interpretability in neural networks.
method Adaptive Group Lasso for feature selection.
result Consistent feature selection for neural networks with theoretical guarantee.
Study compares neural networks for stock selection using fundamental ratios.
problem Predicting stock performance using fundamental financial ratios.
method Comparative study of feed-forward neural network (FNN) and adaptive neural fuzzy inference system (ANFIS).
result Both FNN and ANFIS can separate winners and losers, but FNN performs better.
Anisotropic neural network selects relevant features from datasets.
problem Reduction of irrelevant features improves model interpretability and performance.
method General Regression Neural Network with an anisotropic Gaussian Kernel.
result The method robustly selects features from simulated and real-world datasets.
Proposes a neural network framework for feature selection in high-dimensional settings.
problem Challenges in feature selection and non-linear function estimation in high-dimensional settings.
method Sparse-input neural networks using group concave regularization.
result Establishes finite-sample guarantees for variable selection consistency and prediction accuracy.
A new method accelerates deep neural network training using minimal margin score.
problem Training deep neural networks is computationally expensive.
method Introduces minimal margin score (MMS) for selecting samples.
result Significant acceleration in training deep neural networks.
This paper improves neural machine translation training by selecting and denoising data.
problem Reduces negative impact of noisy data on neural machine translation training.
method Measures and selects domain data, applies denoising curriculum using online data selection.
result Significant effectiveness for training on noisy data.
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.
BSF algorithm reduces neural network size and selects features efficiently.
problem Neural network size and feature selection optimization.
method Binary Stochastic Filtering (BSF) layer that penalizes information, stochastically passes or drops features.
result Multifold decrease in neural network size and optimal feature selection.
Automates neural network model selection for efficiency.
problem Efficiently choosing neural network architectures and hyper-parameters.
method Modified micro-genetic algorithm for automated model selection.
result AMS finds efficient neural network models for classification and regression.
Bayesian neural networks learn smaller models with comparable predictive performance.
problem Model selection in Bayesian neural networks, particularly choosing the number of nodes.
method Applied a horseshoe prior to select nodes in a Bayesian neural network.
result The horseshoe prior effectively prevents under-fitting without sacrificing predictive or computational performance.
A new feature selection method using attention for neural networks.
problem Feature selection for neural networks with a budget constraint.
method Sequential Attention: greedy forward selection with attention weights.
result Achieves state-of-the-art results for neural networks.
LassoNet selects features in neural networks using Lasso regularization.
problem Making neural networks interpretable by selecting only relevant features.
method LassoNet uses a modified objective function with constraints to enforce feature selection directly during parameter learning.
result LassoNet significantly outperforms state-of-the-art methods for feature selection and regression.
This work extends neural networks to automatically select features by stochastically penalizing feature involvement.
problem Feature selection in machine learning models.
method Stochastic regularization to select features instead of layer weights.
result Superior efficiency compared to classical methods with minimal computational overhead.
Max-plus operators improve neural network filter selection and pruning.
problem Improving neural network efficiency and reducing redundancy.
method Exploiting Max-plus operators in neural network layers for filter selection and model pruning.
result Max-plus layers enhance filter selection and reduce redundancy without performance loss.
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.
Regularizing for or against class selectivity in DNNs improves test accuracy.
problem The necessity and sufficiency of class selectivity in DNNs.
method Direct regularization of class selectivity in convolutional neural networks.
result Reducing class selectivity improves test accuracy, while increasing it decreases it.
SeNA-CNN prevents forgetting in CNNs by selectively augmenting networks.
problem Preventing catastrophic forgetting in neural networks.
method Selective network augmentation to learn new tasks without forgetting old ones.
result SeNA-CNN outperforms state-of-the-art Learning without Forgetting algorithms in some scenarios.
NeuralCut learns to select cutting planes by looking ahead, outperforming traditional methods.
problem Selecting effective cutting planes for MILP optimization.
method Imitation learning on a lookahead expert to train a neural network for cut selection.
result NeuralCut outperforms standard baselines in cut selection for MILP benchmarks.
A trainable gate optimizes neural network selection and pruning.
problem Optimizing neural networks for specific tasks.
method Introduces a trainable gate function to make discrete selection problems differentiable.
result Efficiently optimizes arbitrary neural networks across various tasks.
Deep-gKnock uses DNNs to select groups of features with improved interpretability.
problem Feature selection in high-dimensional data with grouping structure.
method Combines deep neural networks with Knockoffs technique for group-feature selection.
result Improves interpretability and accurate gFDR control compared to state-of-the-art methods.
MARS automatically selects tensor decomposition ranks, improving performance in neural network tasks.
problem Determining optimal decomposition ranks in tensor decompositions.
method MARS uses binary masks to learn optimal tensor structure during training via relaxed MAP estimation.
result MARS achieves better results than previous methods in various tasks.
Study on recurrent neural networks' feature selection and memorization using F1B test.
problem Conflict between feature selection and memorization in sequence learning.
method Flagged-1-Bit (F1B) test, four recurrent network models studied analytically and experimentally.
result Conflict can be resolved by gating mechanism or increasing state dimension.
NGMs create mirrored features to assess neural network feature importance.
problem Lack of feature relevance information in DNNs limits their applicability.
method Structured perturbation and kernel-based conditional dependence measure for feature importance evaluation.
result Controls feature selection error rate and maintains high selection power with correlated features.
Bayesian principles improve neural additive models for better feature selection and uncertainty.
problem Lack of calibrated uncertainties and feature selection in neural additive models.
method Augmenting NAMs with Bayesian principles to provide credible intervals, feature selection, and interaction ranking.
result Improved performance on tabular datasets and real-world medical tasks.
New batch selection strategy improves deep learning model performance.
problem Training deep neural networks efficiently.
method Submodular function maximization for mini-batch selection.
result Deep models trained with proposed batch selection outperform SGD and baseline.
DNN nodes selection improved using gLasso regularization.
problem Selecting important nodes in DNN hidden layers.
method Applied gLasso regularization to DNN weights, compared with L2 regularization.
result gLasso successfully selected necessary and sufficient hidden layer nodes.
RNNs guide clause selection in proof trees, improving inference accuracy.
problem Improving inference accuracy in proof trees.
method Recurrent Neural Networks (RNNs) encode literals to select clauses.
result RNNs outperform gradient boosted trees in clause selection.
Improved survival analysis using square root Cox's models and neural networks.
problem Feature selection in survival analysis.
method Square root Cox's survival analysis by the fittest linear and neural networks model, directly tuning penalty parameter λ.
result Substantially improved over traditional methods, achieving phase transition in feature selection.
This study enhances sales forecasts by integrating market indicators into forecasting models.
problem Traditional forecasting models rely solely on historical demand data.
method Automated integration of macroeconomic time series data (GDP growth) into forecasting models using feature selection methods.
result Feature selection methods, especially Forward Feature Selection, significantly improve forecasting accuracy.
SEISM tests neural network features for regulatory genomics.
problem Testing neural network features for regulatory genomics.
method Selective inference procedure for sequence motifs.
result Sampling under specific parameters characterizes composite null hypothesis.
PINNACLE optimizes point selection for PINNs, improving accuracy.
problem Challenges in selecting points for training Physics-Informed Neural Networks (PINNs).
method Introduces PINNACLE, an algorithm that jointly optimizes collocation and experimental points selection, adjusting point proportions dynamically.
result PINNACLE outperforms existing methods in forward, inverse, and transfer learning problems.
Optimizes tensor rank selection for neural network compression.
problem Finding optimal tensor rank for regression models.
method Analyzes population expressions for training-testing discrepancy under Gaussian design.
result Optimal rank minimizes prediction error and aligns with cross-validation.
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.
Neural Bayes methods simplify fitting complex bivariate extremal models.
problem Inference on complex multivariate extremal dependence models with computationally expensive likelihood functions.
method Use neural networks to approximate Bayes estimators and classifiers for model selection.
result Proposed neural Bayes methods enable routine implementation of complex extreme-value dependence models.
A simple thresholding technique improves graph selection in neural connectivity studies.
problem Graphical model selection for functional neural connectivity in the presence of latent variables.
method Apply a hard thresholding operator to graphical Lasso, neighborhood selection, or CLIME estimators.
result Thresholded estimators outperform existing methods in graph selection consistency and empirical results.
D2NN selectively executes neurons to optimize accuracy and efficiency.
problem Balancing accuracy and computational efficiency in deep neural networks.
method D2NN uses controller modules to selectively execute a subset of neurons based on input, trained with a combination of backpropagation and reinforcement learning.
result D2NNs can effectively optimize accuracy-efficiency trade-offs across various image classification tasks.
SelectiveNet optimizes deep neural networks with a built-in reject option.
problem Selective prediction in deep neural networks.
method End-to-end training of a deep neural architecture to optimize both classification and rejection.
result Improved risk-coverage trade-off over various datasets.
Graph neural networks improve online planner selection for AI tasks.
problem Selecting the best planner for AI tasks.
method Graph Neural Network (GNN) for planner selection and adaptive scheduling.
result Improved planner selection and scheduling for cost-optimal planning.
Attention-based CNNs improve band selection in hyperspectral images.
problem Selecting informative bands from hyperspectral images for accurate classification.
method Attention-based convolutional neural networks reusing activations at different depths.
result Deep models with attention mechanisms achieve high-quality classification and identify significant bands.
LMoE uses LLMs to improve stock trading by selecting experts based on textual and price data.
problem Traditional neural network-based router selection in MoE models is suboptimal and ignores textual data.
method Proposes LLMoE, using LLMs as routers to select experts based on historical price data and stock news.
result LLoM outperforms state-of-the-art MoE models and other deep neural network approaches.
Proposes a method to optimize neural network structures and parameters.
problem Challenges in selecting and designing neural network structures.
method Probabilistic modeling to generate network structures and optimize their parameters.
result The method can find appropriate and competitive network structures.
Proposes a Bayesian approach for automatic node selection in sparse neural networks.
problem Reduces structural complexity and computational speedup in large-scale predictive models.
method Uses spike-and-slab Gaussian priors and variational Bayes approach for node selection.
result Establishes variational posterior consistency and optimal contraction rates for sparse networks.
New method selects facts in proofs using stateful recurrent neural networks.
problem Selecting facts for proving new goals over large formal libraries.
method Stateful architecture based on recurrent neural networks with data augmentation.
result Significantly better performance and solving many new problems compared to previous methods.
Stock selection improved with a novel neural model capturing continuous stock dynamics.
problem Lack of continuous stock dynamics prediction and implicit cross-domain dependencies.
method StockODE, a latent variable model with NRODEs and hierarchical hypergraph for continuous stock volatility and inter-domain dependencies.
result Significantly outperforms baselines, improving Sharpe Ratio by up to 18.57%.
NDF uses deep learning to pick the best data for training.
problem Choosing the right data for efficient model training.
method Deep reinforcement learning framework ( extbf{NDF}) for adaptive data selection.
result NDF improves model performance with less data and fewer iterations.