Genetic Programming constructs features for physics experiments, improving classification accuracy.
problem Lack of interpretable feature construction for experimental physics.
method Combining Genetic Programming with dimensional consistency constraints.
result Constructed features improve classification accuracy by a significant margin.
Enhances machine learning for high-energy physics data by embedding feature construction.
problem Improving machine learning performance in high-energy physics data analysis.
method Integrates feature construction directly into tree-based model training, adapting to physics constraints.
result Significant improvement in classification scores with fewer interpretable features.
Paper builds a physical model of a foliation theory concept.
problem Describing and visualizing the Reeb foliation.
method Geometric methods for 3D printing.
result First comprehensive physical model of the Reeb foliation.
GJMS operators connect geometry, analysis, and physics.
problem None explicitly stated; focus on operators and their impact.
method Construction of conformally invariant differential operators.
result GJMS operators have significant impact in geometry, analysis, and physics.
Develops neural networks for learning physics of complex systems by enforcing thermodynamics principles.
problem Learning physics of complex systems from incomplete experimental data.
method Integrates port-metriplectic formalism with neural networks to enforce thermodynamics principles.
result Neural networks can learn physics of complex systems by parts, reducing learning burden.
The paper connects neural networks to physics using probability theory.
problem Creating neural networks that follow physical laws.
method Applying the central limit theorem and Gaussian process theory to neural networks.
result Neural networks can be designed to obey physical laws by choosing appropriate activation functions.
Paper constructs exotic spacetimes with same physical properties.
problem Whether two topologically identical manifolds can have different geometries.
method Computational approach to produce physical models on exotic spheres.
result Lorentzian metrics on homeomorphic but not diffeomorphic manifolds with same physical properties.
The author exposes the metrical multi-time Lagrange geometry of physical fields which naturally generalizes the classical Lagrangian developped by Miron and Anastasiei. In other words, one constructs a natural theory of physical fields on the 1-jet fibre bundle, attached to a Kronecker h-regular multi-time Lagrangian w…
A new method combines multifidelity techniques to improve model accuracy with limited data.
problem Improving model accuracy with sparse accurate observations and stochastic simulation models.
method Combines bifidelity and CoKriging methods to estimate empirical statistics and construct a Gaussian process.
result Preserves linear physical constraints up to an error bound, leading to accurate model construction.
This review discusses G2-Manifolds and their role in M-Theory compactifications.
problem Understanding the mathematical structure of G2-Manifolds for M-Theory compactifications. method Mathematical and physical considerations of G2-Manifolds and their compactifications. result Progress in constructing and understanding G2-Manifolds. This talk reviews some mathematical and physical ideas related to the notion of dimension. After a brief historical introduction, various modern constructions from fractal geometry, noncommutative geometry, and theoretical physics are invoked and compared.
Light-based attacks can misclassify images without altering physical objects.
problem Physical attacks on deep learning classifiers are limited by the ability to modify inputs directly.
method Constructs an experimental setup with a light projection source, object, and camera. Uses differential evolution to select light patterns.
result Projected light can degrade classification accuracy from 98% to 22% for 2D objects and from 89% to 43% for 3D objects.
PICN learns physical fields from shallow neural networks, improving AI in multi-physical systems.
problem Challenges in modeling and forecasting multi-physical systems due to data scarcity and noise.
method Physics-informed convolutional network (PICN) combining CNN and physical laws, using deconvolution and convolution layers.
result PICN effectively solves and estimates nonlinear physical operator equations and recovers physical information from noisy observations.
AI helps build particle physics theories more efficiently.
problem Building viable particle physics theories requires extensive effort and intuition.
method Developed AMBer, a reinforcement learning framework interacting with physics software.
result AMBer constructs viable models with fewer parameters, validating in neutrino theories.
Improves machine learning models by incorporating physical laws into feature maps.
problem Lack of model interpretability in classical machine learning approaches.
method Physics-informed feature maps constructed from physical laws and dimensional analysis.
result Enhanced model interpretability and potential discovery of new physical equations.
Methods estimate physical load and fatigue from wearable data.
problem Estimating physical load and fatigue from wearable data.
method Statistical and machine learning methods based on kurtosis-skewness diagram.
result Different levels of physical activities and fitness can be distinguished from the kurtosis-skewness diagram.
Physics-guided models improve lake temperature and quality predictions.
problem Predicting and monitoring water temperature and quality in lakes.
method Combining physics-based models and recurrent neural networks with physical constraints.
result Improved prediction accuracy and scientific consistency.
New sampling scheme improves ML accuracy in physics simulations.
problem Improving accuracy of ML models in physics simulations.
method Taylor-based data sampling scheme for DNNs.
result Reduces error in DNN solutions of ODE systems.
Unified physics field theories through a general conservation law.
problem Unified physics field theories.
method Introduced general field as a formal sum of differential forms, defined conservation law using action principle.
result Physics field theories become instances of the general conservation law.
Study finds physical momentum portfolios in Indian stock market yield higher returns than benchmarks.
problem Determining abnormal returns for physical momentum portfolios in the Indian stock market.
method Constructed physical momentum portfolios for daily, weekly, monthly, and yearly timescales, evaluated historical returns and risk profiles.
result Daily time scale physical momentum portfolios showed the strongest reversal with a 16-fold profit.
We introduce various quantitative and mathematical definitions for price momentum of financial instruments. The price momentum is quantified with velocity and mass concepts originated from the momentum in physics. By using the physical momentum of price as a selection criterion, the weekly contrarian strategies are imp…
The aim of this paper is to create a large geometrical background on the dual 1-jet space J^{1*}(T,M) for a multi-time Hamiltonian approach of the electromagnetic and gravitational physical fields. Our geometric-physical construction is achieved starting only from a given quadratic Hamiltonian function of polymomenta H…
A robot learns environmental fields using physics-based models and Bayesian methods.
problem Accurately learning complex environmental fields from limited robot measurements.
method Bayesian framework with Gaussian processes to select and update physics-based models in real-time.
result The robot's learned flow field approximates real flow better than prior solutions and data-driven methods.
Paper integrates ML with physics models for engineering and environmental challenges.
problem Complex science and engineering problems require new methodologies combining physics-based models and ML.
method Structured overview of integrating physics-based models with ML techniques.
result Taxonomy of existing techniques and potential research gaps identified.
In this paper, we study the perturbative aspects of the half-twisted variant of Witten's topological A-model coupled to a non-dynamical gauge field with Kahler target space X being a G-manifold. Our main objective is to furnish a purely physical interpretation of the equivariant cohomology of the chiral de Rham complex…
This paper introduces a framework for combining scientific knowledge of physics-based models with neural networks to advance scientific discovery. This framework, termed physics-guided neural networks (PGNN), leverages the output of physics-based model simulations along with observational features in a hybrid modeling …
Unified access package for fundamental physics datasets simplifies machine learning.
problem Lack of unified access to datasets from multiple fundamental physics disciplines.
method Unified Python package with common interface and reference models.
result Graph-based neural networks perform similarly to dedicated methods on various datasets.
Study axisymmetric waves on extremal Kerr spacetime using physical-space estimates.
problem Obtain integrated local energy decay estimates for axisymmetric waves on extremal Kerr backgrounds.
method Use physical-space analysis and a method introduced by Stogin, simplifying Aretakis' derivation.
result Extend Morawetz estimates to extremal Kerr spacetime using purely classical currents.
We find ways to make physical signals misclassified by computer vision models.
problem Vulnerability of signal classifiers to adversarial perturbations in physical signals.
method Solving PDE-constrained optimization problems to construct imperceptible perturbations.
result Effective and physically realizable adversarial perturbations can be computed for machine learning models.
New algebraic structures called cyclic Lie-Rinehart algebras are defined.
problem Defining new algebraic structures.
method Construct Lie-Rinehart algebras with a specific cyclic submodule.
result Found a connection to differential operators in physics.
Quantum character varieties unify four construction methods.
problem No specific problem stated; unification of approaches.
method Four different approaches to construction.
result Unified understanding of quantum character varieties.
PhIK uses physics models to improve Gaussian process regression.
problem Improving Gaussian process regression for complex systems.
method Constructs non-stationary Gaussian processes from physics models, avoiding hyperparameter optimization.
result Guaranteed physical constraints in predictions and error estimates.
L-GATr transforms high-energy physics data using geometric algebra and Lorentz symmetry.
problem Extracting scientific understanding from particle-physics experiments with high precision and efficiency.
method L-GATr, a geometric algebra Transformer, representing data in 4D space-time and being equivariant under Lorentz transformations.
result L-GATr achieves performance comparable to or better than domain-specific baselines on regression, classification, and generative tasks.
We constructed physically stable sp2 negatively curved cubic carbon structures which reticulate a Schwarz P-like surface. The method for constructing such crystal structures is based on the notion of the standard realization of abstract crystal lattices. In this paper, we expound on the mathematical method to construct…
Deep learning framework for uncertainty quantification in physics.
problem Uncertainty in systems governed by non-linear differential equations.
method Physics-informed neural networks with adversarial inference.
result Effective training of deep generative models for physical systems.
This paper presents a continuous variable generalization of the Aoki-Yoshikawa sectoral productivity model. Information theoretical methods from the Frieden-Soffer extreme physical information statistical estimation methodology were used to construct exact solutions. Both approaches coincide in first order approximatio…
The study explores properties of a specific type of spacetime.
problem Discussing geometric and physical properties of hyper-generalised quasi-Einstein spacetime.
method Analyzing various types of pseudosymmetry and Ricci symmetry over the spacetime.
result Proved the existence of a non-trivial hyper-generalised quasi-Einstein spacetime.
Efficiently accelerates Feldman-Cousins method using Gaussian processes.
problem Slow computation of confidence intervals in high-energy physics.
method Gaussian process acceleration of Feldman-Cousins method.
result Confidence intervals can be computed 5-10 times faster with similar accuracy.
Physics-constrained neural nets solve EM fields of charged particle beams.
problem Solving Maxwell's equations for intense charged particle beams.
method 3D Convolutional Neural Networks (CNNs) constrained by physics.
result 3D CNNs generate electromagnetic fields from current and charge densities.
LDDNN learns physical dynamics from data without exact solutions.
problem Learning physical dynamics from data without exact solutions.
method LDDNN topology that learns Lagrangian density from data.
result LDDNN can learn physical dynamics from data.
Constructs a triple on an Atiyah algebroid with connection.
problem Dynamics of systems on principal bundles and Atiyah algebroids.
method Constructs a Tulczyjew triple on a principal bundle with connection, then reduces to the Atiyah algebroid.
result Dynamics of systems on principal bundles and Atiyah algebroids are discussed and applied.
Bayesian model uses physics constraints for semi-supervised surrogate learning.
problem Lack of labeled data in fine-grained model training.
method Probabilistic generative model with virtual observables.
result Enables semi-supervised training with unlabeled data.
Physics-informed GP regression solves eigenvalue problems by identifying non-trivial eigenspaces.
problem Solving eigenvalue problems of linear operators with trivial solutions.
method Constructing a transfer function-type indicator using physics-informed Gaussian Process posterior.
result The posterior covariance is non-trivial only for eigenvalues of the operator, indicating non-trivial eigenspaces.
Bayesian hybrid models correct for missing physics in machine learning.
problem Systematic bias in machine learning models.
method Fusing physics-based insights with machine learning constructs, using Bayesian calibration and stochastic programming.
result Bayesian hybrid models outperform pure machine learning approaches with less data.
This thesis develops the theory of bundle gerbes and examines a number of useful constructions in this theory. These allow us to gain a greater insight into the structure of bundle gerbes and related objects. Furthermore they naturally lead to some interesting applications in physics.
GINNs combine deep learning with PGMs for physics-based multiscale systems.
problem Intrinsic computational bottlenecks and lack of sufficient data for QoI estimation.
method Hybrid approach combining deep learning with probabilistic graphical models, informed by structured priors for CVs.
result GINNs produce tight confidence intervals for non-Gaussian QoIs.
Efficient surrogate modeling for complex PDEs with physical laws.
problem High computational cost of repeated PDE simulations.
method LC-prior Gaussian process with POD and RBF-FD.
result Significantly reduced computational cost and improved accuracy.
Paper designs Poisson integrators using machine learning.
problem Designing integrators that preserve Poisson geometry.
method Reformulated as an optimization problem in Hamilton-Jacobi PDE, solved using machine learning.
result Machine learning approximates solutions to Hamilton-Jacobi PDE.