Deep clustering outperforms conventional networks in singing voice separation.
problem Challenging music source separation tasks.
method Combining deep clustering and conventional networks for better performance.
result Hybrid network outperforms both components.
Quadratic neurons enhance deep networks' approximation capabilities.
problem Improving deep networks' expressive power and efficiency.
method Introduced quadratic neurons and analyzed their performance in deep quadratic networks.
result Quadratic networks can approximate functions more efficiently and uniquely than conventional networks.
DRN outperforms conventional neural networks in distribution regression tasks.
problem Improving performance of distribution regression models.
method Theoretical analysis and comprehensive experiments on DRN compared to conventional neural networks.
result DRN consistently outperforms conventional neural networks in generalizability.
Neural networks outperform conventional filters in inertial sensor-based attitude estimation.
problem Limited accuracy in inertial sensor-based attitude estimation due to dynamic and static motion.
method Investigated neural networks versus conventional filters for improving accuracy.
result Neural networks outperform conventional filters only with domain-specific optimizations.
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.
A new neural network model for ordinal regression.
problem Ordinal regression with non-proportional odds.
method Interpretable neural network for both continuous and discrete responses, training a non-linear neural network as a coefficient function.
result N3POM preserves interpretability while offering flexibility. New method converts conventional ANNs to SNNs with minimal loss and efficiency.
problem Difficulty in training SNNs directly from conventional ANNs due to discreteness.
method Proposes a novel pipeline combining threshold balance and soft-reset mechanisms for efficient conversion.
result Achieves almost no accuracy loss with only 1/10 of typical SNN simulation time.
Paper transforms deep rectifier networks into shallow ones for analysis.
problem Understanding the complexity of deep neural networks.
method Transformation of deep rectifier networks into shallow ones.
result Shallow networks can represent deep networks with fewer functions.
SVD-RND detects blurred images better than conventional methods.
problem Blurred images can fool conventional OOD detection schemes.
method Constructs a novel RND-based detector that uses blurred images during training.
result SVD-RND outperforms baseline detectors in various domains.
New DNN method accelerates image processing optimization.
problem Optimizing large-scale inverse problems in image processing.
method Trains a deep neural network to learn parameters for scaled gradient projection method.
result Significantly improves convergence rate of optimization methods.
EPINET improves neural networks with less computation.
problem Efficiently estimating uncertainty in neural networks.
method Introduces EPINET architecture that augments any neural network with minimal additional training.
result EPINET outperforms large ensembles with significantly less computation.
Neural networks reduce DBP complexity in fiber optics.
problem Complexity in digital backpropagation implementations.
method Neural-network-based approach to implement DBP.
result Learned DBP reduces complexity by 32x100 km fiber-optic link.
Novel topology optimization using CWGANs reduces computational cost.
problem Efficiently optimizing structures with minimal computational resources.
method Conditional Wasserstein GANs (CWGANs) integrated with conventional topology optimization.
result CWGANs enable optimization with reduced computational expense.
This paper addresses credit valuation adjustment with a new closeout convention.
problem Accurate estimation of financial claim value considering counterparty credit risk.
method Theoretical and computational analysis of a nonlinear valuation system using neural networks.
result A neural network-based algorithm effectively solves the high-dimensional nonlinear valuation system.
Study examines adversarial robustness of ANN variants, revealing differences in black-box settings.
problem Adversarial robustness of alternative neural network architectures.
method Analysis of conventional, stochastic ANNs, and SNNs across three datasets; experiments in white-box and black-box settings.
result Stochastic ANNs are more robust than conventional ANNs in black-box settings, especially with surrogate attacks.
Stochastic LWTA networks resist adversarial attacks while maintaining accuracy.
problem Adversarial robustness of neural networks.
method Replaced ReLU with stochastic LWTA activations, trained with Variational Bayesian and PGD.
result Stochastic LWTA networks achieve state-of-the-art robustness against adversarial attacks.
Wide neural networks can degrade performance, contrary to conventional wisdom.
problem Understanding the limitations of increasing network width in neural networks.
method Using Deep Gaussian Processes to decouple capacity and width, analyzing their effects on representational power and non-Gaussianity.
result Wide neural networks can become less adaptable and more Gaussian, leading to performance degradation.
A fast method for learning MZI parameters in optical neural networks.
problem Time-consuming learning of MZI parameters in optical neural networks.
method Customized complex-valued derivatives and a chain rule for Wirtinger derivatives, incorporated into a function module.
result 20 times faster learning compared to conventional AD in MNIST task.
KANOP uses KANs to efficiently price American options.
problem Efficiently pricing American options with limited data.
method Combines KANs with LSMC to estimate continuation value.
result KANOP provides more accurate option value estimates.
Introduces variance layers to improve neural network performance and robustness.
problem The reliance on expected values for predictions and the limitations of conventional stochastic neural networks.
method Introduces variance layers where weights follow a zero-mean distribution and are only parameterized by their variance.
result Variance layers can learn well, serve as an efficient exploration tool, and provide a decent defense against adversarial attacks.
Machine learning method characterizes network interference in A/B tests.
problem Compromised A/B test reliability due to network interference.
method Causal network motifs and machine learning models.
result Outperforms conventional methods in characterizing network interference.
Bayesian approach improves neural network recurrence.
problem Improving neural network recurrence mechanisms.
method Introducing Bayesian recurrence relations and gates.
result Bayesian approach can perform as well as or better than conventional recurrent networks.
Study shows MSE with sigmoid can match SCE in classification tasks, especially with noisy data.
problem Inconsistent errors in neural network classification tasks.
method Introduced Output Reset algorithm to use MSE with sigmoid activation.
result MSE with sigmoid activation achieves comparable accuracy and convergence rates to Softmax Cross-Entropy, especially in noisy data scenarios.
Efficiently trains deep CNNs on conventional hardware.
problem Lack of labeled data and specialized hardware for deep learning.
method Random convexification and frequency-domain minimization.
result Linear scaling with image size, filters, and filter size.
Wavelet Networks learn from raw time-series data, outperforming conventional CNNs.
problem Learning from raw time-series data efficiently and effectively.
method Constructing scale-translation equivariant neural networks based on wavelet symmetries.
result Wavelet Networks outperform conventional CNNs on raw waveforms and spectrograms.
Adaptive learning method improves classification in time series data analysis.
problem Improving classification capability in time series data analysis.
method Embedding adaptive learning method into recurrent temporal DBN.
result Higher classification capability than conventional methods.
A decoder helps interpret neural network layers.
problem Understanding the output of neural network layers.
method Developed a Classifier-Decoder (ClaDec) architecture.
result Reconstructed images from ClaDec are more relevant for classification.
Physics-informed ESNs improve chaotic system prediction accuracy.
problem Predicting chaotic systems while adhering to physical laws.
method Integrates physics constraints into ESN training through an additional loss function.
result Physics-informed ESNs predict chaotic systems with a 2 Lyapunov time improvement.
Loihi neuromorphic chip outperforms conventional hardware in keyword spotting efficiency.
problem Benchmarking keyword spotting efficiency on neuromorphic hardware.
method Comparative analysis of a two-layer neural network trained to recognize a single phrase on Intel's Loihi neuromorphic chip and conventional hardware devices.
result Loihi outperforms conventional hardware on energy cost per inference for this keyword spotting application.
Spatio-temporal RBF neural networks improve chaotic time series prediction.
problem Predicting chaotic time series due to their dynamic nature.
method Proposes an spatio-temporal extension of RBF neural networks.
result Spatio-temporal RBF outperforms standard RBF in chaotic time series prediction.
Deep neural networks often fit low-frequency functions, contrary to conventional numerical schemes.
problem Understanding the implicit bias of deep neural networks in fitting training data.
method Fourier analysis perspective applied to DNNs training process.
result Deep neural networks tend to fit training data by low-frequency functions, contrary to conventional numerical schemes.
Deep neural networks improve sEMG-based hand gesture classification.
problem Accurate classification of hand gestures from sEMG signals.
method Master-slave architecture with DNNs and synthetic feature data.
result Up to 9% improvement in accuracy with synthetic data.
This research evaluates neural network robustness through loss visualization and a new metric.
problem Neural networks' robustness property is insufficiently investigated compared to adversarial attacks and defenses.
method Loss visualization and a new robustness metric to evaluate model stability.
result The proposed robustness metric provides a more reliable evaluation of model stability, uniformed across different models and settings.
Averaging SGD weights improves deep learning models.
problem Improving deep learning model generalization.
method Simple averaging of SGD weights with cyclical or constant learning rate.
result SWA leads to better generalization and flatter solutions.
Enhanced PINN for brittle fracture modeling using transfer learning.
problem Solving brittle fracture problems in physics.
method Physics-informed neural network (PINN) with variational energy minimization and transfer learning.
result The proposed approach yields better accuracy in predicting crack paths compared to conventional PINN.
Proposes a channel pruning method using attention statistics for deep networks.
problem Manual setting of compression ratios in each layer for deep neural networks.
method Channel pruning based on attention statistics with automatic selection of compression ratio.
result Improved performance in terms of accuracy and computational costs compared to conventional methods.
Paper trains SNNs for classification using first-to-spike decoding.
problem Training SNNs for classification under GLM model.
method Proposes first-to-spike decoding method for SNNs.
result Improves accuracy and efficiency of SNN classification.
A-LSTM improves emotion recognition by better modeling time dependencies.
problem Conventional LSTM's time dependency modeling is limited.
method Proposed A-LSTM for better temporal context modeling in RNNs.
result A-LSTM outperforms conventional LSTM by 5.5% in emotion recognition.
New neural network learns relevant transformations in data, improving object recognition.
problem Current equivariant architectures consider all possible transformations, ignoring relevant ones.
method Co-attentive equivariant neural networks that focus on co-occurring transformations.
result Outperforms conventional equivariant networks on rotated MNIST and CIFAR-10.
Combines deep learning and iterative methods for robust phase retrieval.
problem Recovering signals from noisy Fourier intensities.
method Regularization-by-denoising combining iterative phase retrieval and deep learning.
result Outperforms other noise-robust phase retrieval algorithms.
GANs improve image generation from text and other images.
problem Improving image generation from text and other images.
method Adversarial training to estimate real data distribution and generate synthetic data.
result GANs outperform conventional methods in image generation.
Bayesian neural networks approximate Gaussian, this method adapts to non-Gaussian posteriors.
problem Bayesian neural networks struggle with non-Gaussian posteriors, leading to poor performance.
method Proposes a Riemannian Laplace approximation to adapt to the shape of the true posterior.
result Consistently improves over conventional Laplace approximation across tasks.
A new decentralized federated learning approach tackles network capacity challenges.
problem Efficiently utilizing network capacities between nodes in federated learning.
method Proposes a segmented gossip approach for decentralized federated learning.
result Demonstrates significant reduction in training time compared to centralized federated learning.
This paper uses deep neural networks for one-class classification by splitting normal data into typical and atypical subsets.
problem Training deep neural networks with only one class of data for one-class classification.
method Intra-class splitting to create typical and atypical subsets, using binary loss and auxiliary subnetworks.
result The method outperformed seven baselines and had comparable performance to state-of-the-art methods on image datasets.
Simpler GNNs with low-rank non-parametric aggregators perform well on graph benchmarks.
problem Over-engineering in GNN architectures for common semi-supervised node classification datasets.
method Replacing feature aggregation with a non-parametric learner to streamline GNN design.
result Non-parametric regression is effective for semi-supervised learning on sparse, directed networks.
PIELM uses deep learning to solve PDEs quickly and accurately.
problem Solving partial differential equations (PDEs) efficiently and accurately.
method Physics Informed Extreme Learning Machine (PIELM) for solving PDEs.
result PIELM matches or exceeds the accuracy of Physics Informed Neural Networks (PINNs) on various problems.
Researchers create adversarial examples to deceive iris recognition systems.
problem Tackling the vulnerability of iris recognition systems to adversarial attacks.
method Developed a deep auto-encoder surrogate network to generate adversarial examples for iris recognition systems.
result Demonstrated that adversarial examples can fool iris recognition systems in both white-box and black-box settings.
Deep learning improves gamma-ray energy estimation and event selection.
problem Improving gamma-ray event selection and energy estimation.
method Adapted convolutional neural networks (CNN) for gamma-ray astronomy.
result Significant improvement in gamma-ray energy estimation and event selection.