Neural networks can separate non-separable data using feature maps.
problem Non-separable data in neural networks.
method Characterization of feedforward neural networks and use of feature maps.
result ReLU neural networks can separate concentric data.
Convolutional Neural Processes improve data efficiency in neural processes.
problem Improving data efficiency in neural processes for small datasets.
method Convolutional Neural Processes (ConvNPs) improve data efficiency by leveraging translation equivariance and convolutional neural networks.
result ConvNPs enhance the performance of neural processes in small-data problems.
New bound for neural nets on non-iid data.
problem Generalization of deep nets for dependent data.
method Establishes a generalization bound for feed-forward neural networks on φ-mixing data. result Proves neural nets can generalize well on non-iid data.
COIN++ compresses multiple data types efficiently.
problem Handling diverse data modalities in neural compression.
method Implicit neural representations and modulations quantization.
result Significant compression gains with reduced encoding time.
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.
Simplicial neural networks extend graph neural networks to handle higher-order interactions.
problem Handling higher-order interactions in complex data structures.
method Define a convolution operation for simplicial complexes and use it to construct convolutional neural networks.
result SNNs effectively impute missing data in coauthorship complexes.
We develop a neural network model to classify liver cancer patients into high-risk and low-risk groups using genomic data. Our approach provides a novel technique to classify big data sets using neural network models. We preprocess the data before training the neural network models. We first expand the data using wavel…
Graph neural networks extend neural Bayes estimators to irregular spatial data.
problem Estimating parameters from irregular spatial data with computational efficiency.
method Employing graph neural networks to approximate Bayes estimators for irregular spatial data.
result Extending neural Bayes estimation to irregular spatial data with computational benefits.
Proposes a deep neural network for spatial data regression.
problem Regression of spatial data using deep neural networks.
method Localized two-layer deep neural network for spatial data, proving consistency and asymptotic convergence.
result Asymptotic convergence rate is faster than existing methods, demonstrating effectiveness on temperature estimation.
FNNs detect EEG signals without position dependence.
problem Detecting EEG signals without position dependence.
method Shift invariant functional neural networks (FNNs) using FDA methods.
result FNNs outperform FDA benchmarks in EEG classification.
New neural network models for functional data.
problem Handling non-linear functional data.
method Functional Direct Neural Network (FDNN) and Functional Basis Neural Network (FBNN) with gradient-based optimization.
result Demonstrated effectiveness in complex functional models.
A hybrid neural network improves robustness in estimating vehicle parameters from noisy data.
problem Estimating parameters of a mechanical vehicle model from noisy acceleration data.
method Introduced a convolutional neural network with two objective functions: naive and hybrid.
result The hybrid objective function outperforms the naive one in robustness on noisy input data.
Study measures impact of data and neural net similarity on transferability in restaurant sales data.
problem Identify indicators for successful transferability of neural nets across different data sets.
method Empirical study on sales data from six restaurants, calculating indicators based on data and neural net similarities.
result Negative correlations between transferability and indicators, allowing better model performance and fewer transfers.
Traditional Recurrent Neural Networks assume vectorized data as inputs. However many data from modern science and technology come in certain structures such as tensorial time series data. To apply the recurrent neural networks for this type of data, a vectorisation process is necessary, while such a vectorisation leads…
Neural NMF discovers hierarchical topics in multilayer data.
problem Detecting latent hierarchical structure in multilayer data.
method Recursive application of nonnegative matrix factorization (NMF) in layers with backpropagation optimization.
result Neural NMF outperforms other hierarchical NMF methods in synthetic and real-world datasets.
Decodes neural activity to detect context effects in natural settings.
problem Detecting context-dependent changes in neural encoding.
method Decoding-based approach controlling for confounding factors.
result Demonstrates context-dependent changes in neural encoding.
Deep neural nets can estimate regression with dependent data without the curse of dimensionality.
problem Regression with dependent data and structural assumptions on the regression function.
method Deep recurrent neural network estimate under suitable structural assumptions.
result Deep neural nets can circumvent the curse of dimensionality for regression with dependent data.
Improved neural PDEs trained on augmented data enhance model accuracy and efficiency.
problem Training neural PDEs on limited data to accurately represent complex systems.
method Space-filling sampling of local states to generate augmented training data.
result Data-augmented neural PDEs outperform traditional emulators in accuracy and stability.
New method reconstructs significant parts of training data from neural networks.
problem Understanding and reconstructing training data from neural networks.
method Proposes a novel reconstruction scheme based on recent theoretical results about neural network training.
result Shows that a significant fraction of training data can be reconstructed from neural network parameters.
CupNet prunes neural nets for cup-shaped data.
problem Pruning neural networks for cup-shaped data.
method Used simulated cup drawing data to prune a neural network.
result Pruning effectively reduces network size for cup-shaped data.
Paper benchmarks quantum neural networks against classical ones for binary classification tasks.
problem Comparing quantum neural networks with classical ones for binary classification.
method Evaluated with two toy examples, focusing on model complexity and training data size.
result EQNN and QNN outperform ENN and DNN for smaller parameter sets and training data samples.
New method sparsifies hybrid neural ODEs for better performance and stability.
problem Excessive latent states and interactions from mechanistic models lead to training inefficiency and over-fitting.
method Automatic state selection and structure optimization combining domain-informed graph modifications with data-driven regularization.
result Improved predictive performance and robustness with desired sparsity.
SSNAS finds neural architectures without labeled data.
problem Limited labeled data for NAS.
method Self-supervised learning for NAS.
result Comparable results to supervised NAS with labeled data.
Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications …
New method uses unlabelled data to improve Bayesian Neural Networks.
problem Lack of ability to use unlabelled data in conventional Bayesian Neural Networks.
method Self-supervised Bayesian Neural Networks using contrastive pretraining and variational lower bound optimization.
result Prior predictive distributions capture problem semantics better and improve predictive performance.
The paper uses neural networks to learn system dynamics from data with Lipschitz regularization.
problem Learning governing equations from time-sampled data.
method Lipschitz regularized deep neural networks for ODE system identification.
result Lipschitz regularization improves the smoothness and generalization of the learned function.
In domains such as health care and finance, shortage of labeled data and computational resources is a critical issue while developing machine learning algorithms. To address the issue of labeled data scarcity in training and deployment of neural network-based systems, we propose a new technique to train deep neural net…
Neural networks improve geospatial data analysis by relaxing linearity assumptions.
problem Traditional geospatial analysis assumes linear models, limiting flexibility.
method Embedding neural networks within traditional geostatistical models for non-linear mean functions.
result NN-GLS algorithm provides consistent and scalable predictions for irregular spatial data.
Proposes a deep neural network for multi-dimensional functional data classification.
problem Classifying multi-dimensional functional data with non-Gaussian distributions.
method Trains a deep neural network on the principle components of the training data.
result FDNN achieves minimax optimality when log density ratio has a locally connected modular structure.
Research on neural networks has gained significant momentum over the past few years. Because training is a resource-intensive process and training data cannot always be made available to everyone, there has been a trend to reuse pre-trained neural networks. As such, neural networks themselves have become research data.…
PE-GQNN improves spatial data prediction and uncertainty quantification.
problem Poor calibration of predictive distributions in spatial data models.
method Combines PE-GNNs with Quantile Neural Networks and recalibration techniques.
result PE-GQNN outperforms existing methods in predictive accuracy and uncertainty quantification.
BNP extends Neural Processes using bootstrap to better model uncertainty.
problem Limitation of NP in modeling stochastic processes with a single latent variable.
method Introduces BNP by incorporating bootstrap to estimate uncertainty without assuming a specific form.
result Demonstrates improved flexibility and robustness of BNP on various data types.
Nonparametric neural-network estimation of current-status data
problem Estimation of conditional cumulative distribution function with current-status data
method Neural-network sieve maximum likelihood estimator
result Explicit convergence rate for Hölder smoothness
Study the effects of data parallelism and sparsity on neural network training.
problem Understanding the effects of data parallelism and sparsity on neural network training.
method Conducted extensive experiments and developed a theoretical analysis.
result Found a general scaling trend between batch size and number of training steps to convergence for the effect of data parallelism, and difficulty of training under sparsity.
Bayesian neural networks help quantify prediction uncertainties in neural models.
problem Uncertainty in neural network predictions due to model randomness and lack of knowledge.
method Bayesian statistical framework to categorize uncertainty.
result Errors in neural network predictions can be obtained and characterized.
This work characterizes how data augmentation shapes neural representations.
problem Understanding the impact of data augmentation on neural network representations.
method Embedding neural network hidden representations into a metric space invariant to transformations, analyzing shape-space trajectories.
result Increasing data augmentation strength leads to well-behaved trajectories in the embedded space, and different augmentation types steer representations in distinct directions.
Robust deep neural networks estimate multi-dimensional functional data robustly.
problem Estimating location function from multi-dimensional functional data robustly.
method Deep neural networks with ReLU activation, robust to outliers and model misspecification.
result Uniform convergence rates for robust deep neural network estimators.
There has been a recent trend in training neural networks to replace data structures that have been crafted by hand, with an aim for faster execution, better accuracy, or greater compression. In this setting, a neural data structure is instantiated by training a network over many epochs of its inputs until convergence.…
One-pass SGD converges in overparametrized neural networks with random data.
problem Understanding convergence of SGD in neural networks with streaming data.
method Overparameterized two-layer neural networks, one-pass SGD, random initialization, NTK eigen-decomposition, VC dimension, McDiarmid's inequality.
result Prediction error converges in expectation under one-pass SGD in overparametrized neural networks.
New neural model processes 2D data with long-range dependencies efficiently.
problem Limited receptive field of convolutions for complex 2D tasks.
method Proposes Matrix Shuffle-Exchange network with O(logn) layers and O(n2logn) complexity. result Exceeds convolutional and graph neural network baselines in long-range dependency modeling.
The paper develops a neural network-based method for detecting change points in large-scale time-evolving data.
problem Detecting and locating change points in multivariate time-evolving data.
method Two-step procedure involving neural network training and test error function calibration over moving windows.
result Consistent estimates for the number and locations of change points under temporal dependence.
Neural networks improve loss reserving with case estimates and transaction data.
problem Improving loss reserving accuracy using neural networks.
method Comparison of feed-forward and recurrent neural networks trained on case estimates and transaction data.
result Case estimates significantly improve predictions, but memory-equipped neural networks offer minimal additional benefit.
This work explains neural collapse in shallow neural networks and its impact on generalization.
problem Understanding neural collapse in shallow neural networks and its effect on generalization.
method Analysis of two and three-layer ReLU neural networks, focusing on data dimension, sample size, and signal-to-noise ratio.
result Neural collapse occurs in shallow ReLU networks under certain conditions related to data properties and network architecture.
We draw a formal connection between using synthetic training data to optimize neural network parameters and approximate, Bayesian, model-based reasoning. In particular, training a neural network using synthetic data can be viewed as learning a proposal distribution generator for approximate inference in the synthetic-d…
Bayesian neural networks with data augmentation show a persistent cold posterior effect.
problem Understanding the cold posterior effect in Bayesian neural networks with data augmentation.
method Developed principled Bayesian neural networks using data augmentation, providing exact likelihoods and tight bounds.
result The cold posterior effect persists even in models incorporating data augmentation, suggesting it's not an artifact.
NN-CUSUM detects changes in high-dimensional data using neural networks.
problem Detecting abrupt changes in high-dimensional data.
method Neural network-based CUSUM for online change-point detection.
result NN-CUSUM performs well in detecting changes in high-dimensional data.
Bayesian neural networks outperform calibrated neural networks for tabular data.
problem Uncertainty in neural network predictions for tabular data.
method Bayesian neural networks vs. post-hoc calibration methods.
result Bayesian neural networks yield competitive performance compared to calibrated neural networks.
DAERNN models censored data using neural networks with data augmentation.
problem Handling censored data in expectile regression.
method Data augmentation based Expectile Regression Neural Networks (ERNNs).
result DAERNN outperforms existing censored ERNNs methods and achieves comparable predictive performance to fully observed data.