Paper introduces a noise-robust classification method using hypergraph neural networks.
problem Noisy label learning problem in image datasets.
method PCA for dimensionality reduction, then applies graph-based semi-supervised learning methods including hypergraph neural network.
result Our proposed hypergraph neural network achieves the best performance when noise level increases.
Develops neural network for directed hypergraphs for node classification.
problem Irregular data structure, particularly directed graphs.
method Directed hypergraph neural network and semi-supervised learning method.
result Novel directed hypergraph neural network achieves highest accuracies on node classification tasks.
A new interpolation method speeds up neural ODE training.
problem Efficiently approximating gradients in neural ODEs.
method Interpolation-based technique to approximate gradients.
result Our method trains neural ODEs faster than the reverse dynamic method.
New method uses graph neural networks for neural architecture search.
problem Finding optimal neural architectures efficiently.
method Bayesian graph neural network for feature extraction and graph Bayesian optimization.
result Significantly outperforms existing methods in benchmark tasks.
Paper introduces method to make neural networks symmetrical.
problem Creating symmetrical neural networks for data with inherent symmetries.
method Introduces a method for modifying neural networks to enforce equivariance.
result Group convolutional neural networks are a special case of the introduced framework.
Proposes a new method for uncertainty estimation in neural networks.
problem Estimating uncertainty in neural networks.
method Samples outputs from Gaussian distributions parametrized by mean and variance sub-layers.
result Achieves better uncertainty quality than other methods.
Proposes a method to improve neural architectures reproducibly.
problem Lack of reproducibility in Neural Architecture Transformer (NAT).
method Differentiable Neural Architecture Transformation (DNAT).
result DNAT outperforms NAT and is applicable to various models and datasets.
A new GGN method speeds up training of deep neural networks for regression tasks.
problem Training deep neural networks efficiently for regression problems.
method Proposes a Gram-Gauss-Newton (GGN) algorithm for overparameterized neural networks.
result For sufficiently wide neural networks, GGN achieves quadratic convergence rate.
Neural nets solve electric field in non-convex microfluidic devices.
problem Solving differential equations in non-convex geometries.
method Neural network approximation of electric potential and field.
result Deep neural networks outperform shallow networks in accuracy.
Neural networks improve nonparametric regression with measurement errors.
problem Nonparametric regression with measurement errors.
method Proposes a neural network design using FNN, normalizing flow, and inference network.
result Neural network approach is more flexible and superior or comparable to classical methods.
Proposes a method to control model complexity in neural network optimization.
problem Reduces the computational cost of neural architecture search.
method Probabilistic model-based dynamic optimization with a penalty term to control model complexity.
result The proposed method controls model complexity while maintaining performance.
Although artificial neural networks have occasionally been used for Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) studies in the past, the literature has of late been dominated by other machine learning techniques such as random forests. However, a variety of new neural net techniques along with suc…
Neural policy gradient methods converge globally and sublinearly.
problem Global optimality and convergence of neural policy gradient methods.
method Actor-critic schemes with neural networks, proving global optimality and sublinear convergence rates.
result Neural natural and vanilla policy gradient methods converge to globally optimal policies and stationary points.
A new method uses deep neural networks for estimating individual treatment effects.
problem Estimating individual treatment effects in large models.
method Extended fiducial inference with Double Neural Network (Double-NN) method.
result The Double-NN method outperforms CQR in individual treatment effect estimation.
New attack method improves neural network security.
problem Vulnerability of deep neural networks to adversarial attacks.
method Ensemble adversarial attack with long-term gradient memory.
result Enhanced robustness against adversarial attacks.
We propose a simple method that combines neural networks and Gaussian processes. The proposed method can estimate the uncertainty of outputs and flexibly adjust target functions where training data exist, which are advantages of Gaussian processes. The proposed method can also achieve high generalization performance fo…
Investigates the relationship between ResNets and Neural ODEs, quantifying their closeness and providing training methods.
problem Quantifying the distance between ResNet dynamics and Neural ODE solutions.
method Bounding the distance between hidden state trajectories and Neural ODE solutions, using gradient descent and Heun's method.
result Gradient descent and Heun's method can implicitly regularize ResNets towards Neural ODEs, especially for smooth residual functions.
SurvBeNIM explains survival models using neural networks.
problem Explaining predictions of survival models.
method Extends Beran estimator with neural importance functions.
result Improved explanation of survival models compared to existing methods.
New method reduces neural image compression run-time by 50%.
problem Computational efficiency of neural image compression models.
method Automatic network optimization to reduce decoder complexity.
result Decreased decoder run-time by over 50%.
RNNs are reinterpreted as kernel methods using neural ODEs.
problem Improving generalization and stability of RNNs.
method Connecting RNNs to neural ODEs and reproducing kernel Hilbert spaces.
result RNNs can be viewed as linear functions of a specific feature set.
New method improves neural network robustness with brain-like learning.
problem Traditional methods struggle with robustness in adversarial attacks.
method Generalized likelihood ratio method with brain-like learning mechanisms.
result Significant improvement in robustness of neural networks.
Derivative-free method uses deep neural nets for solving PDEs.
problem Solving elliptic partial differential equations (PDEs) without derivatives.
method Trains a deep neural network using reinforcement learning guided by a probabilistic PDE representation.
result Demonstrates effectiveness on various test problems.
New taxonomy and evaluation of neural network compression methods.
problem Efficiency of deep neural networks in real-world applications.
method Categorization and evaluation of tensor factorization and probabilistic compression methods.
result SVD and probabilistic compression methods are complementary and give the best results.
Neural circuits integrate continuous dynamics efficiently.
problem Efficiently integrating continuous neural dynamics for simulation and learning.
method Compact neural circuits for Runge-Kutta and Adams-Bashforth-Moulton methods.
result Equivalence of neural and numerical integration for polynomial systems.
New method shows AdaGrad converges globally to neural network minima.
problem Convergence of adaptive gradient methods for neural networks.
method Proposed adaptive gradient method for over-parameterized neural networks.
result Converges to global minimum in polynomial time for two-layer networks.
Method measures weight similarity in neural networks using normalization and statistical inference.
problem Quantifying weight similarity in non-convex neural networks.
method Chain normalization rule and hypothesis-training-testing statistical inference.
result Weights of identical neural networks converge to similar local solutions.
New method for neural network uncertainty quantification using empirical Neural Tangent Kernel.
problem Accurately quantify uncertainty in neural network predictions.
method Post-hoc, sampling-based approach using gradient-descent on linearized networks.
result Method effectively approximates Gaussian process posterior and outperforms existing methods in efficiency and accuracy.
New method for scalable stochastic neural networks using Kronecker Flow.
problem Scaling stochastic neural networks to high dimensions.
method Kronecker Flow, a scalable parameterization of noise generation.
result Competitive performance on various tasks compared to existing methods.
Bayesian method learns neural network architecture parameters.
problem Estimating optimal neural network architecture parameters.
method Bayesian learning of concrete distributions over layer size and network depth.
result Regular networks with learnt structure generalize better on small datasets, while stochastic networks are more robust to initialisation.
TSSM splits neural networks for parallel training with minimal accuracy loss.
problem Accuracy degradation in parallel training of deep neural networks.
method TSSM reformulates alternating minimization to achieve parallelism with minimal accuracy loss.
result TSSM achieves significant speedup without accuracy loss on multiple datasets.
New DDMs use neural networks for solving equations on manifold shapes.
problem Solving equations on complex, high-dimensional shapes.
method Physics-informed neural networks combined with domain decomposition methods.
result Validated methods work well on various shapes in high dimensions.
Bayesian Neural Networks help quantify uncertainty in deep learning predictions.
problem Uncertainty quantification in deep learning predictions.
method Bayesian statistics applied to neural networks.
result Design, implementation, training, and evaluation of Bayesian Neural Networks.
Proposes volumization for neural networks to control bias-variance tradeoff.
problem Improving generalization and preventing memorization in neural networks.
method Defines a physical volume for weights, interpolating between L2 and L∞ regularization.
result Volumization interpolates between weight decay and clipping, improving generalization.
A method for faster neural architecture search using low-fidelity training.
problem Time-consuming evaluations in neural architecture search.
method Bayesian multi-fidelity method with knowledge distillation.
result Training for a few epochs with knowledge distillation leads to better architecture selection.
SEF method generates prediction intervals by shifting error function in neural networks.
problem Quantifying uncertainty in neural network predictions.
method Training a neural network three times to generate upper and lower bounds, using a parameter from initial estimates.
result SEF method effectively produces prediction intervals, outperforming other methods in evaluations.
Gibbs pruning optimizes neural networks by combining physics and regularization.
problem Large neural networks are impractical for many applications.
method Combines statistical physics and stochastic regularization to train and prune networks simultaneously.
result Gibbs pruning achieves state-of-the-art performance on ResNet-56.
Efficient PI for neural networks without distributional assumptions.
problem No distributional assumptions for efficient predictive inference.
method Differential privacy and linear approximation for leave-one-out models.
result Rigorous coverage guarantees with reduced computation.
Quantum method improves neural density estimation in high dimensions.
problem High-dimensional density estimation with poor performance and high computational complexity.
method Adaptive Fourier features based on quantum density matrices, integrated with neural networks.
result Competitive performance compared to state-of-the-art methods in various datasets.
GNPs use graph neural networks to predict target points with uncertainty quantification.
problem Predicting points on graphs with uncertainty.
method Graph Neural Processes (GNP) that operate on graph data, taking context features and outputting a target point distribution.
result GNPs can quantify uncertainty in graph data predictions.
Proposes methods to add constraints to neural networks to improve stability and generalization.
problem Improving stability and generalization of neural networks.
method Constraint-based regularization using stochastic gradient Langevin dynamics.
result Constraints help stabilize and improve the robustness of deep neural networks.
Study compares uncertainty estimation methods for Bayesian Neural Networks.
problem Quality of uncertainty quantification in Bayesian Neural Networks.
method Empirical comparison of 10 inference methods on regression and classification tasks.
result Common inference metrics can be misleading, and methods designed to capture posterior structure do not always produce high-quality approximations.
New method prunes neural networks while conserving resources.
problem Design efficient neural networks for edge devices with limited computational power.
method Iterative channel-wise pruning with holonomic constraint in Lagrangian multipliers framework.
result Reduction of 15.47 GMAC to 3.87 GMAC for VGG-16 with only 1% top-1 accuracy loss.
New method speeds up deep neural networks inference.
problem Inference speed of deep neural networks.
method Maximum volume algorithm for reduced-order modeling.
result Convolutional layers can be replaced with smaller fully-connected layers with minimal accuracy loss.
This paper explores optimization methods for deep learning.
problem How to effectively train neural networks.
method Discusses gradient explosion/vanishing, initialization, normalization, SGD, adaptive gradient methods, distributed methods, and global issues.
result Provides theoretical insights and practical solutions for neural network training.
Neural networks outperform kernel methods in classifying high-dimensional Gaussian mixtures.
problem Classifying high-dimensional Gaussian mixtures using kernel methods and neural networks.
method Theoretical analysis and derivation of learning dynamics for 2LNN and comparison with kernel methods.
result 2LNN can achieve near-optimal performance on high-dimensional Gaussian mixture classification tasks, surpassing kernel methods.
Survey of data augmentation techniques for time series classification with neural networks.
problem Small datasets in time series recognition.
method Four families of data augmentation: transformation-based, pattern mixing, generative models, and decomposition methods.
result Empirical evaluation of 12 data augmentation methods on 128 datasets.
New attribution method for neural networks using causal principles.
problem Understanding the impact of features on neural network outputs.
method Viewing neural networks as Structural Causal Models, computing causal effects efficiently.
result Efficient computation of feature impacts on neural network outputs.
Review of mean-field methods for neural network inference.
problem Understanding neural network learning from a theoretical perspective.
method Mean-field methods, high-temperature expansions, replica method, message passing algorithms.
result Equivalences and complementarities of mean-field methods.