Cartesian neural network models learn soft tissue mechanical properties without shape assumptions.
problem Model-based methods limit elastography to imaging linear-elastic parameters.
method Data-driven neural network constitutive models (NNCMs) learn stress-strain relationships from force-displacement data.
result NNCMs can characterize mechanical properties and their spatial distribution without prior shape knowledge.
TANNs integrate thermodynamics into ANN models for accurate, consistent predictions.
problem Lack of rigorous physics-based approach in ANN constitutive modeling.
method TANNs encode thermodynamics principles in neural network architecture using automatic differentiation.
result TANNs produce thermodynamically consistent predictions without requiring large datasets.
Automated framework generates mechanical models via deep reinforcement learning.
problem Deriving theoretical-consistent, micro-structural-based traction-separation laws.
method Meta-modeling framework using deep reinforcement learning to form graph edges and maximize model score.
result Automated model generation outperforms existing cohesive models and detects hidden mechanisms.
SVD improves neural network optimization.
problem Optimizing neural networks.
method Using SVD as an initial guess for neural network parameters.
result Better optimization results.
PNCs balance tractability and expressiveness in probabilistic modeling.
problem Balancing tractability and expressiveness in probabilistic models.
method Introduce probabilistic neural circuits (PNCs) as a mix of Bayesian networks and neural networks.
result PNCs are powerful function approximators.
Over 50 million scholarly articles have been published: they constitute a unique repository of knowledge. In particular, one may infer from them relations between scientific concepts, such as synonyms and hyponyms. Artificial neural networks have been recently explored for relation extraction. In this work, we continue…
Deep neural network generates molecular structures close to equilibrium.
problem Discovery of atomistic systems with desirable properties.
method Autoregressive, convolutional deep neural network architecture.
result Model generates molecules close to equilibrium for C7O2H10 isomers.
Trained neural networks perform Bayesian reasoning for tasks beyond their initial scope.
problem Performing Bayesian reasoning for tasks outside the trained neural networks' initial scope.
method Used deep generative models as priors and classification/regression networks as constraints. Approximated Bayesian inference through variational or sampling techniques.
result The approach built on top of already trained networks, expanding the addressable questions.
Improved PINNs for solving PDEs with unknown measurement noise.
problem Handling non-Gaussian noise in physics-informed neural networks.
method Jointly train an EBM to learn the correct noise distribution.
result Improved performance in solving PDEs with non-Gaussian noise.
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.
Estimates copula density for complex data distributions.
problem Estimating copula density from observed data.
method Neural network-based copula density neural estimation (CODINE).
result Novel approach capable of modeling complex distributions.
Modeling aortic wall inhomogeneities to predict dissection risks.
problem Predicting localized stress accumulations in the aortic wall due to inhomogeneities.
method Stochastic constitutive model with random field realizations, coupled with a convolutional neural network surrogate.
result The neural network accurately predicts stress distributions and assesses uncertainty in aortic wall stress.
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.
Quantum neural networks generalize better due to flatter parameter space.
problem Generalization in quantum neural networks.
method Mapped feature data to a quantum state, applied unitary evolution, and measured for classification.
result Quantum neural networks have better generalization than classical networks.
Local laGPR speeds up multiscale mechanics simulations without neural networks.
problem High computational costs in multiscale mechanics simulations.
method Local approximate Gaussian process regression (laGPR) combined with FE schemes.
result laGPR offers better accuracy than neural networks for stress predictions.
Ripple Walk Training tackles graph neural network training issues for large and deep graphs.
problem Neighbors explosion, node dependence, and oversmoothing in large and deep GNNs.
method Subgraph-based training framework with Ripple Walk Sampler for high-quality subgraph sampling.
result RWT improves training efficiency and reduces space complexity for deep and large GNNs.
Hierarchical IBP model for Bayesian neural networks in continual learning.
problem Resource allocation in continual learning with dynamic network complexity.
method Indian Buffet process (IBP) and Hierarchical-IBP (H-IBP) priors for structure learning, online variational inference with reparameterization.
result Our model effectively learns the number of weights in each layer, overcoming overfitting and underfitting.
Guarantees sparse recovery for neural networks with iterative hard thresholding.
problem Recovering sparse network weights in neural networks.
method Structural properties of sparse network weights and iterative hard thresholding algorithm.
result Simple iterative hard thresholding algorithm recovers sparse network weights exactly using linear memory.
HOTCAKE compresses CNNs by decomposing kernels into smaller parts.
problem Compressing deep CNNs without significant accuracy loss.
method Input channel decomposition, guided Tucker rank selection, higher order Tucker decomposition, fine-tuning.
result HOTCAKE produces highly compressed CNN models with good accuracy.
ENN uses covariance matrices for gradient-free optimization in neural networks.
problem Efficiently optimizing neural networks without gradient calculations.
method Ensemble Neural Networks (ENN) with EnRML algorithm.
result ENN outperforms traditional BNNs and is robust to small datasets.
Extends neural network verification to non-linear specifications.
problem Certifying richer properties of neural networks.
method Introduces convex-relaxable specifications for verification.
result Effective verification of important properties like energy conservation and semantic consistency.
This paper characterizes how randomized neural networks generalize well in multi-dimensional tasks.
problem Understanding the generalization of randomized neural networks in multi-dimensional tasks.
method Characterizes RSNs as an IGAM formalized by an optimization problem with a regularization functional and loss.
result RSNs generalize well in multi-dimensional tasks, akin to spline regression under certain conditions.
We conduct a large-scale study of language models for chord prediction. Specifically, we compare N-gram models to various flavours of recurrent neural networks on a comprehensive dataset comprising all publicly available datasets of annotated chords known to us. This large amount of data allows us to systematically exp…
Extends XCS with Experience Replay for improved sample efficiency in single-step tasks.
problem Limited use of Experience Replay in XCS for sequential decision problems.
method Integrates Experience Replay into XCS for single-step tasks and analyzes its impact on sequential decision problems.
result Experience Replay improves sample efficiency in single-step tasks but exacerbates issues in sequential decision problems.
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.
Noise balance theory explains SGD's behavior in neural networks.
problem Understanding SGD's navigation in neural network loss landscapes.
method Analyzes minibatch noise and loss function symmetries.
result Derives the stationary distribution of SGD for deep networks.
DSVNP uses global and local latent variables for improved neural process predictions.
problem Limited expressiveness of vanilla neural processes in capturing target-specific local variation.
method Introduces DSVNP combining global and local latent variables for prediction.
result Competitive prediction performance in multi-output regression and uncertainty estimation.
DRE combines DNN with random feature regression for efficient neural network design.
problem Designing and training deep neural networks (DNN) efficiently and effectively.
method DRE architecture with two-layer neural networks, randomly drawn input and output weights trained with linear ridge regression.
result DRE outperforms state-of-the-art DNN in many data sets with lower computational cost.
Much combinatorial optimisation problems constitute a non-polynomial (NP) hard optimisation problem, i.e., they can not be solved in polynomial time. One such problem is finding the shortest route between two nodes on a graph. Meta-heuristic algorithms such as A ∗ A^{*} A ∗ along with mixed-integer programming (MIP) methods …
Deep learning for Venus images uses high-res hyperspectral data to simulate ground truth.
problem Lack of accurate ground truth data for training deep neural networks in remote sensing.
method Unmixing high-resolution hyperspectral images to simulate ground truth for training a CNN.
result The model can classify mid-resolution Venus images successfully.
Random deep neural networks are robust to adversarial examples, scaling with input size and dimension.
problem Adversarial examples challenge the reliability of deep learning algorithms.
method Analysis of random deep neural networks with Gaussian process equivalence and experiments on MNIST and CIFAR10.
result The ℓ p \ell^p ℓ p distance of adversarial examples scales as 1 / d i m e s ℓ p 1/\sqrt{d} imes \ell^p 1/ d im es ℓ p norm of the input. Sparse regression models CMs from oscillatory shear data efficiently.
problem Discovering parsimonious constitutive models from oscillatory shear experiments.
method Sparse regression with tensor basis functions, l1 regularization, and greedy two-stage algorithm.
result Inferred CMs extrapolate well beyond training data and flow conditions.
Novel neural models have been proposed in recent years for learning under domain shift. Most models, however, only evaluate on a single task, on proprietary datasets, or compare to weak baselines, which makes comparison of models difficult. In this paper, we re-evaluate classic general-purpose bootstrapping approaches …
Heart diseases constitute a global health burden, and the problem is exacerbated by the error-prone nature of listening to and interpreting heart sounds. This motivates the development of automated classification to screen for abnormal heart sounds. Existing machine learning-based systems achieve accurate classificatio…
A new method for neural network initialization using graph degeneracy.
problem Improving neural network performance through better initialization.
method Adapted k-hypercore decomposition for neural network initialization.
result k-hypercore outperforms state-of-the-art initialization methods.
Neural networks estimate SDEs with jump noise using a Tamed-Milstein scheme.
problem Estimating drift and diffusion functions in SDEs with jump noise.
method Tamed-Milstein scheme with neural networks as non-parametric approximators.
result Flexible estimation of complex nonlinear dynamics in systems with state-dependent noise.
DMT enhances deep neural networks to better preserve data structures.
problem Preserving geometric, topological, and distributional structures of data in NLDR.
method Deep manifold transformation (DMT) using cross-layer LGP constraints.
result DMT networks outperform existing NLDR methods in preserving data structures.
This work discovers latent field effects governing interacting dynamical systems.
problem Discovering field effects governing interacting dynamical systems.
method Proposes neural fields to learn latent force fields from observed dynamics, disentangling local object interactions and global field effects.
result Accurately discovers latent field effects in various dynamical systems.
Improves LSTM performance by initializing states via manifold learning.
problem Improving LSTM performance through better initialization.
method Learning an intrinsic data manifold to initialize LSTM internal states.
result Improved LSTM performance through consistent initialization.
New method for pricing discrete Asian and Lookback options under Heston model.
problem Efficient pricing of discrete Asian and Lookback options under Heston model.
method Data-driven approach using artificial neural networks and stochastic collocation points.
result High accuracy and significant computational time reduction compared to classical methods.
Piecewise linear activations create many spurious local minima in neural networks.
problem Understanding the loss surface of neural networks with piecewise linear activations.
method Proved the existence of infinite spurious local minima and partitioned the loss surface into smooth cells.
result Piecewise linear activations create many spurious local minima that are invariant under a continuous path.
Deep hedging uses RL to minimize risk in financial markets.
problem Minimizing risk in financial markets using reinforcement learning.
method Trains a neural network policy via Monte Carlo simulation and stochastic gradient descent.
result Deep hedging algorithm falls within the RL category.
New method uses neural networks to learn causal graphs from interventional data.
problem Challenges in learning causal directed acyclic graphs from data.
method Reformulates as continuous constrained optimization, uses neural networks, leverages interventional data.
result Method compares favorably to state of the art in various settings.
Deep learning framework improves accuracy in solid mechanics.
problem Improving accuracy in solid mechanics simulations.
method Physics Informed Neural Networks (PINN) with multi-network model.
result PINN framework leads to more accurate predictions and improved robustness.
Convolutional neural networks improve surgical skill evaluation.
problem Manual feedback from senior surgeons is laborious, expensive, and subjective.
method Fully convolutional neural networks (CNNs) for classifying and regressing surgical skills.
result Deep neural networks achieve competitive performance on JIGSAWS dataset.
Random deep neural networks favor simple functions.
problem Understanding the generalization properties of deep learning.
method Analyzing binary classifiers of random wide deep neural networks with ReLU activation.
result Random deep neural networks are biased towards simple functions.
New method calibrates rough stochastic volatility models quickly.
problem Calibrating rough stochastic volatility models is expensive and time-consuming.
method Combines Levenberg-Marquardt with neural networks for fast calibration.
result Neural network approximates implied volatility map efficiently.
Convex optimization refines neural network training, improving model performance and reducing hyperparameter sensitivity.
problem Training deep neural networks using non-convex optimization methods often leads to suboptimal solutions and requires extensive tuning.
method Formulate neural network training as convex programs with regularization terms, leveraging sparse recovery models and semi-infinite programming theory.
result Convex models can achieve global optima and outperform traditional non-convex methods, with improved robustness to hyperparameters.