Neural net reconstructs dark matter density from halo velocities.
problem Reconstructing local dark matter density from halo velocities.
method Hybrid architecture combining U-Net and DeepSets.
result Hybrid network recovers density amplitudes and phases better than U-Net.
Convolutional attractor nets improve image completion and super-resolution.
problem Construct coherent neural states from noisy data.
method Revisit and extend attractor networks with convolutional bipartite architecture.
result Demonstrates potential for image completion and super-resolution.
DEMO-Net improves graph neural networks by focusing on node degree.
problem Limited analysis of graph convolution properties and lack of degree-specific graph structure.
method Proposes DEMO-Net, a degree-specific graph neural network that recursively identifies 1-hop neighborhood structures and uses multi-task learning for node representation learning.
result Demonstrates effectiveness and efficiency of DEMO-Net on node and graph classification benchmarks.
New tool for interpreting neural nets, explaining model behavior.
problem Interpreting neural network responses and explaining model behavior.
method Full-Gradient representation and FullGrad saliency map approximation.
result FullGrad method explains model behavior more comprehensively and accurately than other methods.
BiGraphNet generalizes graph neural networks for more efficient operations.
problem Fragmented graph neural network architectures hinder optimization.
method Explicitly separates input and output nodes, enabling new efficient operations.
result BiGraphNet accelerates and scales computations in hierarchical networks.
Butterfly-Net improves CNN performance with structured connections and initialization.
problem Improving the performance of convolutional neural networks (CNNs).
method Butterfly-Net introduces structured and sparse cross-channel connections, and Butterfly initialization strategy.
result Butterfly-Net approximates Fourier representations with exponentially decaying error as depth increases.
Convolutional nets require fewer samples than fully-connected nets for image classification.
problem Understanding why convolutional nets are more sample-efficient than fully-connected nets.
method Construction of a natural distribution and target function to demonstrate a sample complexity gap.
result Convolutional nets require O(1) samples for a single target function, while fully-connected nets require Ω(d2) samples. Convex relaxations improve CNNs with fixed weights.
problem Improving CNNs with fixed weights.
method Convex relaxations for CNNs with fixed weights using second order cone programs.
result The relaxation recovers the global minimum under a planted model assumption.
Proposes Π-Nets, polynomial neural networks, for improved representation power.
problem Improving representation power in deep learning models.
method Introduces Π-Nets, a new class of deep polynomial neural networks. result Demonstrates Π-Nets outperform standard DCNNs and achieve state-of-the-art results. CoDA Nets improve interpretability in neural networks.
problem Improving interpretability in neural networks.
method Dynamic Alignment Units (DAUs) for input-dependent linear transformations.
result CoDA Nets achieve on par results with ResNet and VGG models on complex datasets.
MATCH-Net uses CNNs to predict disease trajectories accurately.
problem Inaccurate prediction of disease trajectories in survival analysis.
method Developed a Missingness-Aware Temporal Convolutional Hitting-time Network (MATCH-Net).
result Demonstrated state-of-the-art performance in real-world Alzheimer's data.
New algorithm improves kernel-based deep net performance.
problem Understanding deep learning and its mysteries.
method Exact computation of Convolutional NTK (CNTK) for infinite-width convolutional nets.
result CNTK results in 10% higher performance on CIFAR-10 than previous methods. G-Net constructs binary neural networks with high accuracy using randomized binary embeddings.
problem Creating high-accuracy binary neural networks with theoretical guarantees.
method Proposes a novel floating-point G-Net family with randomized binary embeddings and theoretical accuracy guarantees.
result Empirically, G-Net achieves almost 30% higher accuracy on CIFAR-10 compared to prior HDC models.
Infinitely wide neural nets perform well on small datasets.
problem Performing well on small datasets with limited training samples.
method Using Neural Tangent Kernels (NTKs) for kernel regression.
result NTK SVM outperforms Random Forests and Convolutional NTK on CIFAR-10 with 10-640 training samples.
Neural nets optimize dynamic hedging strategies with transaction costs.
problem Optimal hedging strategy in presence of transaction costs and discrete time.
method Convolutional neural network trained to infer optimal hedging frequencies.
result Dynamic multiscale hedging strategy reduces risk and maximizes profit.
Z-Net improves 3D CT volume segmentation for surgical planning.
problem Discontinuities and class-imbalances in 3D CT volume segmentation.
method Z-Net uses anisotropic spatial separable convolutions to preserve full field-of-view.
result Z-Net achieves up to 12.6% improvement in IoU for CT segmentation.
A new 2.5D U-net for 3D segmentation reduces memory constraints.
problem Large storage requirements for 3D convolutions in neural networks.
method Transform volumetric data into sequences of 2D images, apply 2D convolutions, and reconstruct.
result Outperforms existing methods in volumetric segmentation tasks.
Seq-U-Net improves sequence modeling efficiency with dilated U-Net.
problem Efficiently modeling long-term dependencies in sequences.
method Causal U-Net architecture with dilated filters and slow feature hypothesis.
result Seq-U-Net achieves comparable performance with speed-ups of over 4x in audio generation.
Gradient descent globally optimizes a neural net with Gaussian inputs.
problem Training deep neural networks with gradient descent is hard in general.
method Used gradient descent on a specific neural network architecture with Gaussian inputs.
result Gradient descent converges to the global optimum in polynomial time for Gaussian inputs.
New neural network design improves speech enhancement metrics.
problem Improving speech enhancement metrics in noisy conditions.
method Combination of convolutional and recurrent layers in U-net architecture.
result Proposed solution outperforms current state-of-the-art in SDR, SIR, and STOI metrics.
U-Nets use belief propagation for efficient image denoising and classification.
problem Efficiently denoise and classify images using generative hierarchical models.
method Interpreted U-Nets as implementing belief propagation in tree-structured models.
result U-Nets can efficiently approximate denoising functions with sample complexity bounds.
Lat-Net compresses Lattice Boltzmann simulations using neural networks.
problem High computational and memory demands in fluid simulations.
method Convolutional autoencoders and residual connections in a fully differentiable scheme.
result Computational and memory efficient neural network that generalizes to large grid sizes and complex geometries.
CNN automates vitiligo lesion segmentation quickly and accurately.
problem Manual segmentation of vitiligo lesions is time-consuming and inconsistent.
method U-Net architecture with modified contracting path, followed by watershed algorithm refinement.
result CNN achieves 73.6% Jaccard Index, significantly outperforming state-of-the-art methods.
A new method speeds up spectral normalization for neural nets.
problem Efficiently controlling the spectral norm of convolutional layers.
method Depthwise separable convolutions with spectral normalization.
result Significant reduction in computational and memory costs.
New music dataset for machine learning research.
problem No specific problem stated; focuses on dataset creation.
method Defined a large-scale music dataset and evaluated machine learning architectures.
result End-to-end models learned frequency selective filters.
A CNN with U-Net improves structural topology optimization efficiency and generalization.
problem Structural topology optimization with reduced computation cost and improved generalization.
method Deep Convolutional Neural Network (CNN) with U-Net architecture, using SIMP-generated dataset.
result Significant reduction in computation cost with little sacrifice on design optimality.
A new meta-learning method improves deep neural net training efficiency.
problem Efficient training of complex deep neural networks with long training processes.
method Meta-learning with Hessian-Free (MLHF) approach based on Hessian-Free optimization.
result MLHF shows good and continuous training performance in deep convolution neural nets.
Neural surrogate predicts SPN rates from token trajectories.
problem Challenging parameter estimation in SPNs with covariates.
method 1D Convolutional Residual Network trained on Gillespie-simulated SPN realizations.
result Surrogate predicts rate-function coefficients with RMSE = 0.043.
CDPL-Net integrates CNN and DL for better image representation.
problem Improving image representation learning by combining CNN and DL.
method CDPL-Net architecture combining CNN and DPL layers, using l1-norm for sparse representation, and efficient stochastic gradient descent.
result Enhanced performance compared to state-of-the-art methods.
Researchers shrink U-Net to find limits of retinal vessel segmentation.
problem Improving retinal vessel segmentation with deep learning.
method Modified U-Net with functional blocks, then simplified to extreme conditions.
result U-Net does not degrade until very minimal configurations.
New deep learning methods improve CT image quality from few projections.
problem Sparse-view CT images suffer from streaking artifacts due to limited projections.
method Inspired by deep convolutional framelets, propose new U-Net variants that satisfy the frame condition.
result New U-Net variants provide better reconstruction performance for sparse-view CT.
BCD-Net uses identical CNN structures for image recovery in undersampled imaging.
problem Challenges in obtaining accurate images from undersampled or noisy measurements.
method Incorporates image mapping CNN into BCD signal recovery method using alternating direction method of multipliers.
result Significantly more accurate image recovery compared to existing methods.
We consider ill-posed inverse problems where the forward operator T is unknown, and instead we have access to training data consisting of functions fi and their noisy images Tfi. This is a practically relevant and challenging problem which current methods are able to solve only under strong assumptions on the t…
Paper tackles dermoscopy lesion boundary detection using deep learning.
problem Automatic detection of lesion boundaries in dermoscopy images.
method Adapted U-net convolutional neural network with skip connections.
result Demonstrates effectiveness of deep learning in lesion boundary segmentation.
Convolutional neural network for probabilistic time series forecasting.
problem Forecasting multiple related time series with complex patterns.
method Temporal convolutional neural network with stacked residual blocks and dilated causal convolution.
result Outperforms state-of-the-art methods in accuracy and efficiency.
DGC-SPNs improve SPNs for image data by combining CNNs and SPNs.
problem SPNs struggle with complex spatial relationships in images.
method Integrates CNNs with SPNs, using novel parameterization for dilations and strides.
result Significantly improved feature coverage and resolution compared to existing SPN architectures.
A new CNN method for point cloud data.
problem Processing 3D point cloud data efficiently.
method Creating a mapping of nearest neighbors and applying weights to spatial relationships.
result Achieves a CNN-like architecture for point clouds without extensive feature engineering.
This work finds a point with small test error in polynomial time for mildly overparameterized neural nets.
problem Achieving small test error in mildly overparameterized neural networks.
method The work shows that the landscape of loss functions with explicit regularization has a property that all local minima and certain stationary points achieve small test error. It also proves the existence of polynomial time algorithms for finding such points in convolutional and fully connected neural nets.
result Polynomial time algorithms exist for finding points with small test error in mildly overparameterized neural nets.
Study uses neural networks to predict wall quantities in turbulent flows.
problem Predicting wall quantities in turbulent open channel flows.
method Training convolutional neural networks (FCN) and a proposed R-Net architecture to predict wall-shear-stress and wall pressure.
result R-Net architecture performs better and predicts wall quantities with around 10% error.
FD-Net predicts future dynamics from data using Hessian-Free TRCG method.
problem Discovering hidden partial differential equations from data.
method Finite-difference inspired convolutional neural network with Hessian-Free TRCG method.
result FD-Net predicts future dynamics efficiently using few trainable parameters.
Unified normalization framework improves performance in various neural network tasks.
problem Limited effectiveness of existing normalization techniques in recurrent neural networks.
method Unified divisive normalization framework, including batch and layer normalization, with a sparse regularizer.
result Significant improvements in image classification, language modeling, and super-resolution tasks.
Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high accuracy to be trained. Although previous research showed that shallow feed-for…
A diverse system combines CNNs and meta-nets for handwritten digit recognition.
problem Handwritten digit recognition using diverse classification hypotheses.
method Generate diverse classification hypotheses using CNNs and other techniques, then combine them with Meta-Nets.
result Achieved state-of-the-art performance in handwritten digit recognition.
GMLS-Nets extend CNNs to unstructured data points.
problem Learning from irregularly spaced data points in science and engineering.
method Introducing GMLS for non-parametric estimation and parameterizing it for learning operators with unstructured stencils.
result GMLS-Nets provide a framework for functional regression and quantity prediction from unstructured data.
BCD-Net improves low-dose CT image reconstruction.
problem Challenges in obtaining accurate low-dose CT images.
method Modified iterative regression CNN, BCD-Net, with faster numerical solvers.
result BCD-Net achieves better image quality and generalization than state-of-the-art methods.
IFR-Net improves MRI images with faster, better detail recovery.
problem Fine structure loss in high-speed MRI scans.
method Iterative feature refinement network with trainable parameters and CNN-based inversion blocks.
result Preserves image details and structural information with faster reconstruction.
This work improves optic disc and cup segmentation for glaucoma detection.
problem Automatic segmentation of optic disc and cup on eye fundus images for glaucoma diagnosis.
method Modification of U-Net convolutional neural network.
result Our method achieves comparable quality to state-of-the-art methods, with faster prediction times.
Deep neural networks improve PET attenuation correction from MR images.
problem Challenges in PET attenuation correction from MR images in PET/MR hybrid systems.
method Deep neural networks, specifically U-net and GroupU-net structures, to derive continuous attenuation coefficients.
result Proposed neural network methods outperform standard methods in PET quantification accuracy.