Develops interpretable model for latent stochastic systems from noisy data.
problem Learning interpretable models of latent stochastic dynamical systems from noisy data.
method Semi-parametric model using Gaussian process for drift, inference of latent paths with sparse variational description.
result Flexible nonparametric model of dynamics with interpretable portraits.
Method interprets LSTMs at the cell level for better understanding of their dynamics.
problem Understanding the dynamics of LSTMs at the cell level.
method A systematic pipeline for interpreting individual hidden state dynamics using response characterization methods.
result Identifies neurons with insightful dynamics and quantifies their impact on network performance.
Recurrent-DBN models dynamic relational data with interpretable latent structures.
problem Interpreting dynamic relational data with hidden structures.
method Recurrent Dirichlet Belief Network framework with hierarchical latent structures and efficient inference strategy.
result Recurrent-DBN discovers interpretable latent structures and improves link prediction.
DOODL learns shared spectral dynamics across related dynamical systems.
problem Learning independent dynamical operators for each system limits discovery of shared structure.
method DOODL learns a dictionary of characteristic spectral dynamics on a manifold of related systems.
result DOODL achieves errors one to two orders of magnitude lower than independent operator estimation methods.
GDM models time series with smoother transitions and interpretable states.
problem Capturing smooth, variable-speed transitions and stochastic mixtures of states.
method Introduces a continuous relaxation of discrete states and a Gumbel noise model.
result Models real-world datasets more faithfully with smoother dynamics and interpretable states.
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.
Model learns Lagrangian dynamics from images for better prediction and control.
problem Lack of interpretability and applicability to high-dimensional data like images.
method Unsupervised neural network model that learns Lagrangian dynamics from images using a coordinate-aware VAE.
result Model infers interpretable Lagrangian dynamics, enabling long-term prediction and synthesis of controllers.
Classifies collective motions in biological networks using graph dynamic mode decomposition.
problem Classifying complex collective motions in biological networks based on transient and complexly changing network properties.
method Data-driven spectral analysis (graph dynamic mode decomposition) to extract dynamical properties.
result Contextual node information and physical properties are crucial for classifying collective motions.
Proposes InfoSSM for interpretable unsupervised learning of complex dynamics.
problem Learning complex nonparametric dynamics from multi-modal data.
method InfoSSM framework using multiple Gaussian process transition models and mutual information regularizer.
result Demonstrates improved interpretability and performance in multi-modal dynamics.
Simplified SGD interpretation as Ito process for broader applicability.
problem Lack of generality in current SGD interpretation.
method Introduced a simplified scheme for discrete-time approximation of Ito process.
result Flexibly interprets SGD and SGLD, providing insights into their asymptotic properties.
iLED framework offers interpretable dynamics for multiscale systems.
problem Modeling high-dimensional multiscale systems is challenging.
method Interpretable Learning Effective Dynamics (iLED) framework based on Mori-Zwanzig and Koopman operator theory.
result Comparable accuracy to state-of-the-art approaches with added interpretability.
Develops a new model for multi-scale nonlinear dynamics.
problem Interpretable descriptions vs. accurate predictions in modeling nonlinear systems.
method Tree-structured recurrent switching linear dynamical system with Bayesian inference.
result Models offer both interpretability and accuracy in predicting complex dynamics.
Dynamic CBDT improves treatment effect estimation in clinical data.
problem Estimating heterogeneous treatment effects in observational data with high accuracy and interpretability.
method Dynamic Regularized Causal Boosted Decision Trees (CBDT) integrating variance regularization and calibration.
result Significantly improved estimation accuracy and reliable coverage of true treatment effects.
Automated model predicts C. elegans escape behavior.
problem Complex escape behavior of C. elegans due to rising temperature.
method Phenomenological modeling using Sir Isaac dynamical inference platform.
result Inferred model accurately predicts worm behavior and is biologically interpretable.
DynGraph2Seq predicts health stages from user activity graphs in online forums.
problem Predicting health stages from changing user activities in online forums.
method Formulated user activities as dynamic graphs, used DynGraph2Seq model with hierarchical attention.
result Demonstrated effectiveness and interpretability of DynGraph2Seq.
FAVAE learns disentangled representations from sequential data.
problem Learning disentangled and interpretable representations from sequential data.
method FAVAE uses the information bottleneck principle without supervision.
result FAVAE can disentangle multiple dynamic factors.
Federated learning interprets temporal dynamics across clients with graph attention.
problem Interpreting temporal patterns across decentralized, heterogeneous systems with nonlinear dynamics.
method Graph Attention Network for learning state transition models over latent states communicated between clients.
result First interpretable characterization of cross-client temporal interdependencies in decentralized nonlinear systems.
Interpretable model for Granger causality using neural networks.
problem Inferring Granger causality in complex dynamical systems.
method Extension of self-explaining neural networks for multivariate Granger causality.
result Framework performs on par with baseline methods and better at inferring interaction signs.
Symmetry-regularized Neural ODEs improve model stability and interpretability.
problem Improving the stability and physical interpretability of Neural ODEs.
method Integrating Lie symmetries and conservation laws into the loss function.
result Symmetry-regularized Neural ODEs enhance model stability and interpretability.
The Volterra lattice is considered. New gradient interpretation for this dynamical system is proposed. This interpretation seems to be more natural than existing ones.
Bayesian model improves data-efficiency in reinforcement learning.
problem Data inefficiency in reinforcement learning.
method Bayesian approach with variational inference.
result Human-interpretable insight into reinforcement learning dynamics.
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
PASS model predicts disease progression with both accuracy and interpretability.
problem Balancing accurate disease prediction with clinically interpretable models.
method Phased LSTM units with attention mechanism for non-stationary state dynamics.
result PASS model achieves superior predictive accuracy and interpretable representations.
Paper explores balancing market dynamics and interpretable forecasting models for energy prices.
problem Tackles the challenge of accurately predicting mFRR price and understanding market dynamics.
method Compares XGBoost and EBM for forecasting mFRR activation price in the balancing market.
result EBM provides comparable forecasting accuracy to XGBoost but with higher interpretability.
KTVGL models tensor time series data for interpretable dynamic network estimation.
problem Estimating time-varying dependencies in multi-mode tensor time series data.
method Kronecker Time-Varying Graphical Lasso (KTVGL) for mode-specific dynamic network estimation.
result KTVGL produces interpretable modeling results and higher edge estimation accuracy than existing methods.
We propose a method to infer stochastic low-rank RNNs from neural data.
problem Fitting low-rank RNNs to noisy, stochastic neural data.
method Variational sequential Monte Carlo methods for stochastic low-rank RNNs.
result Lower dimensional latent dynamics compared to state-of-the-art methods.
The paper studies how neural policies can be interpreted using decision trees.
problem Understanding how machine learning controllers make decisions in complex environments.
method The approach involves disentangled representation using decision trees to interpret neural policies.
result The paper shows that disentanglement of learned neural dynamics improves interpretability.
Develops a method to model neural dynamics with flexible yet interpretable latent states.
problem Capturing complex nonlinear dynamics in neural time series while maintaining interpretability.
method Gaussian Process Switching Linear Dynamical System (gpSLDS) that balances expressiveness and interpretability.
result Favorable performance in comparison to rSLDS on synthetic and real neuroscience data.
Linear attention in Transformers can be interpreted as dynamic VAR models.
problem Misalignment between Transformers and autoregressive forecasting objectives.
method Interpreting linear attention as VAR, rearranging MLP, attention, and flow.
result SAMoVAR improves performance, interpretability, and efficiency.
VTIRT speeds up IRT inference for dynamic learner proficiency.
problem Expensive and slow inference algorithms for dynamic IRT models.
method Variational Temporal IRT (VTIRT) for fast, accurate inference.
result Orders of magnitude speedup in inference runtime with accurate results.
Improves latent variable learning for complex data.
problem Expressive latent variables for model prediction on multi-component data.
method Dynamic Latent Separation method that distances data samples in the latent space.
result Enhances output diversity and provides interpretable representations.
Framework learns image dynamics between time steps using latent variables.
problem Challenges in capturing evolving image patterns and temporal information.
method Estimates intermediary image stages using a physical latent variable model.
result Demonstrates robustness and effectiveness in geoscientific imagery.
Proposes neural networks that preserve physical system dynamics.
problem Learning accurate representations of dynamical systems.
method Variational integrator networks designed to preserve geometric structure.
result Accurately learns dynamical systems from noisy observations.
TimeTrail detects financial fraud patterns through temporal correlation analysis.
problem Detecting and explaining complex financial fraud patterns.
method Temporal data enrichment, dynamic correlation analysis, interpretable pattern visualization.
result TimeTrail outperforms conventional methods in accuracy and interpretability.
DAFT models attention as a dynamical system to make neural networks more interpretable.
problem Uninterpretable features learned by neural networks without human priors.
method DAFT models attention as a continuous dynamical system using neural ODEs.
result DAFT reduces the number of reasoning steps while maintaining similar performance.
How can we find patterns and anomalies in a tensor, or multi-dimensional array, in an efficient and directly interpretable way? How can we do this in an online environment, where a new tensor arrives each time step? Finding patterns and anomalies in a tensor is a crucial problem with many applications, including buildi…
MAOP learns object dynamics from raw visual data.
problem Efficient learning of dynamics from raw visual data for multiple objects.
method Three-level learning architecture with spatial-temporal relational reasoning.
result Significantly outperforms previous methods in sample efficiency and generalization.
Reverse engineered RNNs reveal line attractor dynamics for sentiment classification.
problem Understanding how recurrent neural networks solve sequential tasks like sentiment classification.
method Dynamical systems analysis to reverse engineer trained RNNs, identifying fixed points and linearized dynamics.
result Trained RNNs converge to low-dimensional line attractor dynamics, providing interpretable solutions.
The present paper contains an interpretation and generalization of Novikov's theory of Morse type inequalities for 1-forms in terms of Conley's theory for dynamical systems.
Class of Newtonian dynamical systems admitting normal blow-up of points in Riemannian manifolds is considered. Geometric interpretation for weak normality condition, which arose earlier in the theory of dynamical systems admitting the normal shift of hypersurfaces, is found.
S2KAN integrates symbolic primitives into neural network activations for improved interpretability.
problem Training activations in KANs often lack symbolic fidelity, leading to unintelligible models.
method Softly Symbolified Kolmogorov-Arnold Networks (S2KAN) integrates symbolic primitives into training with learnable gates and a Minimum Description Length objective.
result S2KAN discovers interpretable forms when symbolic terms suffice, gracefully degrading to dense splines when necessary.
Bayesian networks handle incomplete and changing data.
problem Handling incomplete and dynamic data.
method Review and application of Bayesian networks to incomplete and dynamic data.
result Bayesian networks can model dynamic and incomplete data.
A new method creates simpler, more interpretable decision trees from complex ensembles.
problem Complex tree ensembles reduce interpretability and control over machine learning models.
method Dynamic-programming based algorithm for finding a minimum-size decision tree.
result Optimal born-again trees are simpler and more interpretable than original ensembles.
Optimized DMD for fast atmospheric chemistry forecasting.
problem Forecasting global atmospheric chemistry dynamics efficiently.
method Optimized Dynamic Mode Decomposition (DMD) for reduced order modeling.
result Significant improvement in computational speed and interpretability.
Explains a 2D color exchange invariant correspondence to 3D linking numbers.
problem Understanding color exchange invariants in 2D dynamics and their 3D geometric interpretation.
method Visualizes invariants as linking of lines on a special surface with Arf-Kervaire invariant one, and interprets it as an obstruction to continuous transformation.
result Interprets a 2D color exchange invariant as a 3D linking number, providing a topological explanation.
Machine learning identified 13 key equations for distillation column dynamics.
problem Identify governing laws for complex engineered systems.
method Sparse Identification of Non-Linear Dynamics (SINDy) applied to distillation column data.
result Reduced 1000s of equations to 13 interpretable terms.
TIME network simplifies complex physical processes with interpretable models.
problem Challenges in learning coupled dynamic processes from multiple observations.
method Fully convolutional architecture capturing invariant domain structure.
result Robust and transparent in capturing process kernels and anomalies.
Study on liquidity dynamics in Uniswap v3 pools using statistical methods.
problem Characterize liquidity in Uniswap v3 pools.
method Functional principal component analysis (FPCA) and dynamic factor methods.
result Liquidity dynamics in Uniswap v3 pools are well-captured by a low-order Legendre polynomial basis.