Neural network learns atomic coordinates from Patterson maps in a simplified case.
problem Training a neural network to infer atomic coordinates from Patterson maps.
method Synthetic data training, centering output maps, removing centrosymmetric inversion, and adding empty space.
result The network can generalize to infer atom positions from Patterson maps not in the training set.
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.
This paper proposes an online knowledge distillation method that transfers feature map information in addition to class probabilities.
problem Previous online knowledge distillation methods only utilized class probabilities, missing feature map information.
method Adversarial training framework to transfer feature map information; multiple networks trained simultaneously with discriminators.
result Our method performs better than direct alignment methods and is more suitable for online distillation.
sFML learns stochastic dynamical systems from data.
problem Learning unknown stochastic dynamical systems from measurement data.
method sFML extends FML for deterministic systems, using a stochastic flow map composed of deterministic and stochastic sub-maps.
result sFML constructs a stochastic evolution model approximating unknown stochastic systems.
Novel approach learns optimal transport using convex neural networks.
problem Learning optimal transport between distributions from samples.
method Solving a minimax optimization to learn two convex functions, representing the optimal transport map.
result The approach finds optimal transport mappings that are independent of initialization and can handle discontinuous distributions.
A novel solve-training framework is proposed to train neural network in representing low dimensional solution maps of physical models. Solve-training framework uses the neural network as the ansatz of the solution map and train the network variationally via loss functions from the underlying physical models. Solve-trai…
Contagion maps detect network structure in noisy data.
problem Detecting underlying manifold structure in noisy data.
method Using activation times in threshold contagions to map network nodes to high-dimensional space.
result Contagion maps reliably detect manifold structure in noisy data, while Isomap fails.
Visualizes deep neural networks for speech recognition using learned topographic filter maps.
problem Unintuitive internal structure of deep neural networks complicates activation visualization.
method Trains a convolutional speech recognition model with filters arranged in a 2D grid, highlighting similar filters.
result Topographic filter maps visualize artificial neuron activations more intuitively.
A neural network method tackles high-dimensional diffeomorphic mapping problems.
problem High-dimensional diffeomorphic mapping struggles with the curse of dimensionality.
method Combines variational principles with quasi-conformal theory for accurate, bijective mappings.
result Validated accuracy, robustness, and effectiveness in complex registration scenarios.
Deep neural network predicts traffic flow on city maps.
problem Short-term traffic flow prediction on high-resolution city maps.
method UNet-based deep convolutional neural network with densely connected layers.
result Best performance on the Traffic4cast challenge 2019.
Generalizes neural networks for infinite-dimensional mappings, including PDE solutions.
problem Learning mappings between infinite-dimensional spaces and finite-dimensional approximations.
method Graph kernel network architecture with message passing for kernel integration.
result Competitive performance compared to state-of-the-art solvers for PDEs.
Equivariant neural networks use symmetry to interpret complex data.
problem Interpreting and understanding the behavior of equivariant neural networks.
method Decompose layers into simple representations and analyze nonlinear activation functions.
result Equivariant neural networks can be interpreted using a filtration generalizing Fourier series.
A new method for joint eQTL mapping and gene network estimation.
problem Discovering SNP-gene relationships and gene-gene relationships in gene expression regulation.
method L1-2 regularized multi-task graphical lasso (L1-2 GLasso).
result Competitive performance on capturing true sparse structures of eQTL mapping and gene network.
The study reveals simplicity bias in neural networks leading to better compositional mappings.
problem Understanding when and how to encourage neural networks to learn compositional mappings.
method Examined compositional mappings through coding length and gradient descent dynamics.
result Neural networks tend to learn the simplest bijections, explaining their good generalization.
Paper introduces a neural network for consistent estimation of optimal transport maps.
problem Statistically consistent estimation of optimal transport maps between probability distributions.
method Lipschitz-constrained GAN penalized by quadratic transportation cost.
result The generator converges uniformly to the optimal transport map as sample size increases.
Improves neural network mapping functionality using latent feature generation.
problem Improving neural network performance in visual recognition tasks.
method Reversible learning for generating and learning latent features.
result The proposed method outperforms existing state-of-the-art methods in visual recognition.
Graph neural network predicts optimal coarse-grained mapping operators.
problem Optimal coarse-grained mapping operators selection for molecular dynamics simulations.
method Graph Neural Network (DSGPM) trained on expert-annotated data.
result DSGPM outperforms state-of-the-art methods in graph segmentation.
In image-based camera localization systems, information about the environment is usually stored in some representation, which can be referred to as a map. Conventionally, most maps are built upon hand-crafted features. Recently, neural networks have attracted attention as a data-driven map representation, and have show…
TCNs can approximate complex input-output maps with limited memory.
problem Approximating complex input-output maps with limited memory.
method Proved TCNs can approximate a wide class of input-output maps with arbitrary error tolerance.
result Deep ReLU TCNs can approximate input-output maps with finite memory to arbitrary error.
The feature map obtained from the denoising autoencoder (DAE) is investigated by determining transportation dynamics of the DAE, which is a cornerstone for deep learning. Despite the rapid development in its application, deep neural networks remain analytically unexplained, because the feature maps are nested and param…
Paper establishes rates of universal approximation for neural tangent kernels using transport mappings.
problem Universal approximation for neural tangent kernels with microscopic weight changes.
method Generic scheme to approximate functions with NTK using transport mappings, constructed via Fourier transforms.
result Approximation of continuous functions with roughly 1 / δ^(10d) nodes, where δ depends on function continuity.
Maps are an important medium that enable people to comprehensively understand the configuration of cultural activities and natural elements over different times and places. Although massive maps are available in the digital era, how to effectively and accurately access the required map remains a challenge today. Previo…
Deep generative priors are a powerful tool for reconstruction problems with complex data such as images and text. Inverse problems using such models require solving an inference problem of estimating the input and hidden units of the multi-layer network from its output. Maximum a priori (MAP) estimation is a widely-use…
Proposes a new method to prevent overfitting in deep neural networks.
problem Overfitting in deep neural networks with many trainable parameters.
method Randomly replaces elements in feature maps with specific values during training.
result Improves the testing performance of deep neural networks on benchmark datasets.
Stochastic neural networks can approximate any function, even with correlated outputs.
problem Approximating functions with stochastic outputs and correlations.
method Investigating deep sigmoid belief networks to approximate any stochastic mapping.
result Minimal number of layers and units needed for approximation.
Neural network outperforms traditional methods in chaotic dynamics classification.
problem Classifying chaotic and regular dynamics of the Chirikov standard map.
method Trained a convolutional neural network on finite-length trajectories compared to traditional Lyapunov exponent computation.
result Neural network outperforms traditional methods for short periods, converging faster and more robustly.
Study neural networks by mapping correlations, revealing essential statistics.
problem Understanding information processing in trained neural networks.
method Characterize neural network as distribution transformations, focusing on correlation functions.
result Higher-order correlations are crucial for internal layers, while input layer captures more.
New nonlinear saliency maps improve deep neural network interpretability.
problem Lack of understanding why and how deep neural networks make decisions.
method Developed novel nonlinear saliency maps to better interpret deep neural networks.
result Nonlinear saliency maps provide more specific drivers of classification on complex examples.
Landmark2Vec maps unknown landmarks without GPS.
problem Estimate positions of unknown landmarks without GPS.
method Unsupervised neural network trained on landmark signals.
result Maps landmarks up to scale, rotation, and shift.
Comprehending complex systems by simplifying and highlighting important dynamical patterns requires modeling and mapping higher-order network flows. However, complex systems come in many forms and demand a range of representations, including memory and multilayer networks, which in turn call for versatile community-det…
New method encodes 3D object geometry into neural network weights for efficient reconstruction.
problem Efficiently representing and reconstructing 3D objects with minimal parameters.
method Mapping network that encodes object geometry into neural network weights, reconstructing objects using simple geometric spaces.
result Reconstructed objects have accuracy comparable to state-of-the-art methods with significantly fewer parameters.
1-Lipschitz neural networks produce clearer, more focused Saliency Maps for explainable AI.
problem Noisy and limited Saliency Maps from traditional neural networks.
method Dual loss of optimal transport problem for 1-Lipschitz neural networks.
result Saliency Maps from 1-Lipschitz networks are highly concentrated and less noisy, aligning with human explanations.
The paper maps time-series onto networks to reveal hidden joint information.
problem Extract hidden joint information from uncorrelated time-series.
method Discretize time-series amplitudes, map onto networks, measure coupling deviations, and compare with Gaussian distributions.
result Markets may possess joint patterns even if initially uncorrelated.
Quantitative susceptibility mapping (QSM) is a powerful MRI technique that has shown great potential in quantifying tissue susceptibility in numerous neurological disorders. However, the intrinsic ill-posed dipole inversion problem greatly affects the accuracy of the susceptibility map. We propose QSMGAN: a 3D deep con…
This paper proves neural networks can approximate any infinite-dimensional map with uniform guarantees.
problem Universal approximation of infinite-dimensional maps by neural networks with uniform guarantees.
method Analysis of various infinite analogues of neural networks and their approximation capabilities.
result Any continuous map can be approximated arbitrarily closely by some infinite neural networks with mild topological conditions.
Fixed points of nonnegative neural networks are analyzed using fixed point theory.
problem Analyzing fixed points in nonnegative neural networks.
method Fixed point theory, nonlinear Perron-Frobenius theory, monotonic and scalable mappings.
result Conditions for the existence of fixed points in nonnegative neural networks are provided.
Deep neural networks improve free energy calculations for peptide conformations.
problem Challenges in developing suitable mappings for free energy perturbation.
method Adapted machine learning approach to train deep neural networks for mapping between Boltzmann distributions.
result Accurate free energy differences calculated between thermodynamic states with spring centers separated by 1 Å and sometimes 2 Å.
SMAPGAN generates styled map tiles from remote sensing images.
problem Generating timely updated map tiles from remote sensing images is challenging.
method Semi-supervised GAN model with gradient loss and ESSI metric.
result SMAPGAN outperforms state-of-the-art methods in quality metrics and human perception.
A method for optimal Bayesian filtering using progressive particle flow and optimal transport maps.
problem Optimizing Bayesian filtering with deterministic particles to avoid degeneration.
method Progressive flow of particles through a sequence of sub-steps, each using an optimal transport map to replace non-equally weighted particles with equally weighted ones.
result The method avoids particle degeneration and simplifies the filtering process by not requiring inversions or monotonicity constraints.
Improved saliency maps for deep neural networks with reduced noise.
problem Noisy explanations in Integrated Gradients for deep neural networks.
method SmoothTaylor, adaptive noising, and SmoothGrad techniques.
result SmoothTaylor and adaptive noising generate better quality saliency maps.
Proposes SOMDAGMM for more accurate network intrusion detection.
problem Inaccurate network intrusion detection in secure network environments.
method Integrates self-organizing map with deep autoencoding Gaussian mixture model.
result SOMDAGMM outperforms state-of-the-art DAGMM with up to 15.58% improvement in F1 score.
New algorithm constrains SOMs to create supervised low-dimensional mappings.
problem Creating supervised mappings in neural networks with known internal topology.
method Developed Supervised Topological Maps (STMs) by modifying SOMs to incorporate target distances.
result STMs allow for supervised generation of new data with known internal structure.
Gatherings of thousands to millions of people frequently occur for an enormous variety of events, and automated counting of these high-density crowds is useful for safety, management, and measuring significance of an event. In this work, we show that the regularly accepted labeling scheme of crowd density maps for trai…
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were proposed to account for this phenomenon, there are few works that provide rigorous ana…
This paper proposes an efficient autoHPO method based on data-to-hyper-parameter mapping.
problem Manual hyper-parameter tuning is costly and dependent.
method The approach is based on mapping from data to hyper-parameters using a sophisticated network structure and effective construction algorithms.
result The proposed approach significantly outperforms state-of-the-art methods.
Characterizes test error in learning with deep, structured feature maps.
problem Characterizing test error in learning with deep, structured feature maps.
method Asymptotic analysis of feature covariance and population covariance.
result Closed-form formula for feature covariance in Gaussian rainbow neural networks.
Riemannian Neural OT maps improve scalability on manifolds.
problem Challenges in extending neural OT to high-dimensional Riemannian manifolds.
method Introduces Riemannian Neural OT (RNOT) maps that avoid discretization and incorporate geometric structure.
result RNOT maps approximate Riemannian OT maps with sub-exponential complexity in the dimension.
A new method quantifies feature-map discriminativeness for efficient pruning of deep neural networks.
problem Efficiently pruning deep neural networks to reduce computation while maintaining accuracy.
method Presented a novel mathematical formulation (Discriminant Information, DI) to quantify feature-map discriminativeness, enabling efficient pruning and intra-layer mixed precision quantization.
result Our pruned ResNet50 achieves 44% FLOPs reduction without any Top-1 accuracy loss.