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.
New algorithm improves interpretability in sequence classification.
problem Lack of human-independent interpretability metrics in sequence classification.
method Combines linear classifiers with background knowledge embeddings to create a new feature space.
result Preserves predictive power while delivering more interpretable models.
MARLeME extracts MARL models into symbolic models for better interpretability.
problem Improving interpretability and explainability of MARL systems.
method Develops a MARL model extraction library that approximates MARL systems with symbolic models.
result Enhanced understanding and inspection of MARL systems and agents.
Interprets coarse symbol and index classes for Callias type operators.
problem Understanding coarse geometry and index classes for Callias type operators.
method Interprets coarse symbol and index classes in terms of K-theory classes of coarse corona.
result Local positivity and invertibility conditions are incorporated into support conditions in K-theory.
ARTEMIS combines deep learning and symbolic reasoning for financial predictions.
problem Lack of interpretability and economic principles in deep learning models in finance.
method Neuro-symbolic framework combining neural operators, stochastic differential equations, and symbolic distillation.
result ARTEMIS achieves state-of-the-art directional accuracy, outperforming all baselines on synthetic crash regime.
OccamNet finds interpretable symbolic fits to data efficiently.
problem Complex neural models extrapolate poorly and are hard to interpret.
method Samples functions, biases towards better fits, and uses cross-entropy matching.
result Outperforms state-of-the-art symbolic regression methods on real-world datasets.
This work identifies and mitigates reasoning shortcuts in Neuro-Symbolic models.
problem Neuro-Symbolic models can achieve high accuracy by using unintended concepts.
method Characterized reasoning shortcuts as unintended optima of the learning objective and identified four key conditions.
result Reasoning shortcuts are difficult to mitigate, casting doubt on NeSy solutions' trustworthiness and interpretability.
The time series classification literature has expanded rapidly over the last decade, with many new classification approaches published each year. The research focus has mostly been on improving the accuracy and efficiency of classifiers, while their interpretability has been somewhat neglected. Classifier interpretabil…
Enhances Cox model for survival analysis with symbolic non-linear log-risk functions.
problem Limited interpretability and non-linearity in traditional Cox models.
method Introduces GCPH model using Kolmogorov-Arnold Networks for symbolic non-linear log-risk functions.
result GCPH achieves competitive performance and superior interpretability.
New models explain image-based questions better with fewer examples.
problem Improving understanding and efficiency in visual question answering.
method Probabilistic neural-symbolic models with interpretable latent programs.
result Models generate more understandable programs with fewer examples and allow probing reasoning.
SDE automatically recovers interpretable discrete distributions.
problem Limited interpretable discrete probability laws.
method Unsupervised framework using symbolic density estimation.
result Accurately recovers interpretable discrete distributions.
We introduce mod 3 triple Milnor invariants and triple cubic residue symbols for certain primes of the Eisenstein number field Q ( − 3 ) \mathbb{Q}(\sqrt{-3}) Q ( − 3 ) , following the analogies between knots and primes. Our triple symbol generalizes both the cubic residue symbol and Rédei's triple symbol, and describes the decomposition…
PAN+SR tackles scalable symbolic regression for large p p p datasets.
problem Symbolic regression struggles with large number of input variables and measurement error.
method Combines ab initio nonparametric variable selection with SR to pre-screen and reduce search complexity.
result PAN+SR consistently enhances 19 SR methods' performance on challenging datasets.
Develops a Bayesian framework for symbolic regression of scientific expressions.
problem Lack of principled uncertainty quantification and interpretability in existing symbolic regression methods.
method Hierarchical Bayesian framework with tree-structured symbolic expressions and Markov chain Monte Carlo inference.
result Robust performance on various datasets, including single-atom catalysis.
Graph networks learn symbolic physics laws from simulations.
problem Learning interpretable physics laws from simulations.
method Inductive biases on graph networks for symbolic regression.
result Graph networks can learn symbolic laws of physics.
Meta-learning approach to learn interpretable models from human feedback.
problem Tackling the challenge of making machine learning models interpretable.
method A meta-learning approach where a model of non-trivial proxies of human interpretability is learned from human feedback, then incorporated into the ML training process to optimize for interpretability.
result The approach leads to formulas that are either significantly more or equally accurate while being more interpretable.
VaSST uses soft symbolic trees for probabilistic symbolic regression.
problem Efficiently recover symbolic expressions from noisy data.
method Variational inference with soft symbolic trees.
result Superior performance in structural recovery and predictive accuracy.
The Wodzicki residue and the cut-off integral extend to classical symbol-valued forms. We show that they obey a Stokes' type property and that the extended Wodzicki residue can be interpreted as a complex residue like the ordinary one. In the case of cut-off integrals, Stokes' property (i.e. vanishing on exact forms) o…
SGE learns symbolic node representations from relational data.
problem Mining insights from complex, real-world systems.
method SGE uses frequent pattern mining on a node's neighborhood to learn symbolic node representations.
result SGE outperforms shallow node embedding methods on a venue classification task.
Kolmogorov-Arnold Networks offer interpretable models for energy applications.
problem Lack of interpretability in modern machine learning methods for sensitive industries.
method Symbolic regression with Kolmogorov-Arnold Networks compared to traditional feedforward neural networks.
result Kolmogorov-Arnold Networks yield perfectly interpretable models and learn real, physical relations.
Neural network learns equations from data, improving interpretability and extrapolation.
problem Combining neural networks and symbolic regression for better model interpretability and extrapolation.
method Integrating a neural network-based Equation Learner (EQL) network with other deep learning architectures.
result The EQL-based architecture can extrapolate well outside of the training data set.
Successful human-robot cooperation hinges on each agent's ability to process and exchange information about the shared environment and the task at hand. Human communication is primarily based on symbolic abstractions of object properties, rather than precise quantitative measures. A comprehensive robotic framework thus…
NeuRules learns interpretable rule lists from data without pre-discretization.
problem Interpretable rule lists for high-stakes decisions in machine learning.
method Neuro-symbolic continuous optimization with temperature annealing.
result NeuRules outperforms existing methods in learning interpretable rule lists.
New linear models improve time series classification efficiency and interpretability.
problem Complex and inefficient classifiers limit interpretability and applicability to variable-length time series.
method Symbolic representations, multi-resolution, multi-domain, linear models.
result mtSS-SEQL+LR achieves similar accuracy to state-of-the-art methods but with lower time and memory usage.
Paper closes neural-symbolic learning loop with grammar model and back-search algorithm.
problem Slow convergence in neural-symbolic learning due to error propagation issues.
method Introduces grammar model as symbolic prior and back-search algorithm for efficient error propagation.
result Significantly outperforms RL methods in performance, converging speed, and data efficiency.
ISR creates analytical relationships from data via invertible maps.
problem Creating analytical relationships from datasets.
method Combines INNs and EQL, using invertible maps and sparsity promoting regularization.
result ISR can serve as a normalizing flow for density estimation and solve inverse problems.
Bayesian symbolic regression uncovers missing physics from data with uncertainty quantification.
problem Incomplete knowledge of physical laws from experimental data.
method Bayesian symbolic regression using Reversible Jump Markov Chain Monte Carlo.
result Uncertainty quantification in recovered model structures.
Active learning improves SR by proposing experiments in data-limited settings.
problem Efficiently gathering data for symbolic regression with physical constraints.
method Query by committee using the Pareto frontier of equations, with physical constraints.
result Reduces data required for SR and achieves state-of-the-art results.
The paper extends Lie bracket to noncommutative geometry using differential operators.
problem Generalizing Lie bracket to noncommutative geometry.
method Antisymmetrizing compositions of vector fields and treating symbols of differential operators.
result Provided necessary and sufficient conditions for jet modules to represent differential operators.
NEMoTS improves time series analysis by deriving efficient, interpretable models.
problem Lack of comprehensive understanding and insightful explanations in time series analysis.
method Neural-enhanced Monte-Carlo Tree Search (NEMoTS) for symbolic regression.
result NEMoTS provides efficient and interpretable models for time series analysis.
ECSEL learns signomial equations for explainable classification.
problem Creating interpretable models for classification.
method ECSEL constructs signomial equations directly for classification and explanation.
result ECSEL outperforms state-of-the-art methods in interpretability and efficiency.
Extract symbolic models from deep learning with inductive biases.
problem Interpreting and discovering physical principles from deep neural networks.
method Introduce strong inductive biases in GNNs, encourage sparse latent representations, apply symbolic regression.
result Extracted symbolic equations from neural networks, including known force laws and new analytic formulas.
The paper models musical motif transformations in Beethoven's works.
problem Understanding how motifs transform in symbolic music.
method Developed a probabilistic framework using Conditional Random Fields.
result Identified patterns of motif transformations and their co-occurrences.
Develops experimental design for discovering missing physics in bioreactors.
problem Discovering missing physics in incomplete model structures of process systems.
method Combines universal differential equations and symbolic regression with sequential experimental design.
result Successfully recovered true model structure of a bioreactor using machine learning techniques.
Combines RNNs and tensor products for sequential data, outperforming state-of-the-art.
problem Improving symbolic interpretation and systematic generalization in natural language reasoning.
method End-to-end training of a recurrent neural network architecture with tensor product representations.
result Significantly outperforms state-of-the-art models in natural language reasoning tasks.
PG-IM uses neural-symbolic programs to manipulate images.
problem Creating holistic image representations and manipulations.
method PG-IM detects patterns, induces symbolic programs, and manipulates images using a neural network.
result PG-IM learns from a single image and achieves superior performance.
We compute the asymptotical growth rate of a large family of U q ( s l 2 ) U_q(sl_2) U q ( s l 2 ) 6 j 6j 6 j -symbols and we interpret our results in geometric terms by relating them to volumes of hyperbolic truncated tetrahedra. We address a question which is strictly related with S.Gukov's generalized volume conjecture and deals with the case of hy…
DCR improves interpretability of concept-based models by using neural networks to build rule structures.
problem Inability of concept-based models to provide transparent decision processes.
method DCR uses neural networks to build syntactic rule structures using concept embeddings and executes these rules on concept truth degrees.
result DCR improves interpretability by up to 25% on challenging benchmarks and discovers meaningful logic rules.
Study evaluates clustering methods for Google Trends data.
problem Clustering high-dimensional, noisy time series data.
method Symbolic Aggregate Approximation (SAX), Enhanced SAX (eSAX), and Topological Data Analysis (TDA).
result TDA provides more balanced and meaningful groupings than SAX and eSAX.
We define the unique (up to normalization) symbol map from the space of linear differential operators on R n R^n R n to the space of polynomial on fibers functions on T ∗ R n T^* R^n T ∗ R n , equivariant with respect to the Lie algebra of projective transformations $sl_{n+1}\subset\Vect(R^n)$ . We apply the constructed s l n + 1 sl_{n+1} s l n + 1 -invariant…
GFN-SR uses deep learning to generate diverse mathematical expressions.
problem Symbolic regression to find best mathematical expressions.
method Traversing a DAG to generate expression trees sequentially with GFlowNet.
result GFN-SR outperforms other SR algorithms in noisy data.
Develops new approach to recover CR structures from their Levi foliations.
problem Recovering CR structures from their Levi foliations for nonregular symbols.
method Reduction to dynamical Legendrian contact structure on leaf space.
result New geometric interpretation of CR prolongation conditions.
Deep Reinforcement Learning (deep RL) has made several breakthroughs in recent years in applications ranging from complex control tasks in unmanned vehicles to game playing. Despite their success, deep RL still lacks several important capacities of human intelligence, such as transfer learning, abstraction and interpre…
Networks of coupled dynamical systems provide a powerful way to model systems with enormously complex dynamics, such as the human brain. Control of synchronization in such networked systems has far reaching applications in many domains, including engineering and medicine. In this paper, we formulate the synchronization…
A novel framework infers causal direction from symbolic sequences using pattern entropy.
problem Challenges in discovering causal direction from temporal symbolic data.
method Dictionary Based Pattern Entropy ( D P E DPE D P E ) framework integrating AIT and Shannon Information Theory. result Minimizing pattern level uncertainty yields a robust framework for causal discovery.
Paper introduces LODE-GPs for modeling data following linear ODEs.
problem Modeling data from systems of linear ODEs.
method Symbolic construction of LODE-GPs using Smith normal form algorithms.
result Improves GP modeling of data from systems of linear ODEs.
A new probabilistic model for semi-supervised learning unifies various methods.
problem Combining different aspects of data distribution for semi-supervised learning.
method A probabilistic model that interprets and improves upon existing SSL methods.
result The model unifies various SSL methods and extends to neuro-symbolic learning.
A new algorithm speeds up sparse regression for discovering equations from data.
problem Learning governing equations from vast data with unsatisfying descriptions.
method SPRINT: a fast algorithm using bisection and analytic bounds to identify optimal rank-1 modifications.
result A calculation that would take millions of years can be done in a day.