New derivation shows how a three-factor learning rule is derived from Oja's rule.
problem Deriving a three-factor learning rule from Oja's rule.
method Using frame theory to systematically derive EGHR-PCA from Oja's rule.
result A principled derivation of a biologically plausible learning rule.
Improved convergence speed of principal component analysis through modified learning rules.
problem Slow convergence for covariance matrices with close eigenvalues.
method Introduced an additional term to the objective function to mitigate convergence issues.
result Significantly improved convergence speed confirmed through simulations.
Unified quadrature framework for large-scale kernel machines.
problem Efficiently approximating kernel functions for large-scale machine learning.
method Deterministic and randomized interpolatory rules for numerical integration of kernel functions.
result The proposed method reduces the number of nodes needed for accurate kernel approximation.
Olshausen and Field (OF) proposed that neural computations in the primary visual cortex (V1) can be partially modeled by sparse dictionary learning. By minimizing the regularized representation error they derived an online algorithm, which learns Gabor-filter receptive fields from a natural image ensemble in agreement …
New method classifies manifold-valued data using Riemannian geometry.
problem Classifying data on curved Riemannian manifolds.
method Probabilistic Learning Vector Quantization on Symmetric Positive Definite Matrices.
result The method outperforms traditional Euclidean methods on manifold-valued data.
Method calculates spectra of Rarita-Schwinger operator on symmetric spaces.
problem Calculating spectra of the Rarita-Schwinger operator on compact symmetric spaces.
method Using Weitzenböck formulas, Laplace operator, Casimir operator, Freudenthal's formula, and branching rules.
result Obtained spectra on the sphere, complex projective space, and quaternionic projective space.
Proposes an alternative method to train RBMs with binary synapses using Bayesian learning rule.
problem Training RBMs with binary synapses is challenging due to discrete nature of synapses.
method Proposes an alternative optimization method using the Bayesian learning rule, updating natural parameters instead of expectation parameters.
result No additional clipping is needed as natural parameters take values in the entire real domain.
A vast majority of computation in the brain is performed by spiking neural networks. Despite the ubiquity of such spiking, we currently lack an understanding of how biological spiking neural circuits learn and compute in-vivo, as well as how we can instantiate such capabilities in artificial spiking circuits in-silico.…
Abstraction and realization are bilateral processes that are key in deriving intelligence and creativity. In many domains, the two processes are approached through rules: high-level principles that reveal invariances within similar yet diverse examples. Under a probabilistic setting for discrete input spaces, we focus …
For a Riemannian submersion from a simple compact Lie group with a bi-invariant metric, we prove the action of its holonomy group on the fibers is transitive. As a step towards classifying Riemannian submersions with totally geodesic fibers, we consider the parameterized surface induced by lifting a base geodesic to po…
We demonstrate the use of several tools from Algebraic Combinatorics such as Young tableaux, symmetry operators, the Littlewood-Richardson rule and discrete Fourier transforms of symmetric groups in investigations of algebraic curvature tensors.
New characterizations of ruled real hypersurfaces in complex projective space found.
problem Characterizing ruled real hypersurfaces in complex projective space.
method Defined tensor fields related to Levi-Civita and generalized Tanaka-Webster connections and studied the structure operator.
result Obtained new characterizations of ruled real hypersurfaces in complex projective space.
The present paper proposes generalized Gaussian kernel adaptive filtering, where the kernel parameters are adaptive and data-driven. The Gaussian kernel is parametrized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of the scalar width parameter. These…
We give a geometric description of the fusion rules of the affine Lie algebra su(2)_k at a positive integer level k in terms of the k-th power of the basic gerbe over the Lie group SU(2). The gerbe can be trivialised over conjugacy classes corresponding to dominant weights of su(2)_k via a 1-isomorphism. The fusion-rul…
We show that for any Legendrian link L in the 1-jet space of S1 the 2-graded ruling polynomial, RL2(z), is determined by the Thurston-Bennequin number and the HOMFLY-PT polynomial. Specifically, we recover RL2(z) as a coefficient of a particular specialization of the HOMFLY-PT polynomial. Furthermore, …
For a positive definite fundamental tensor all known examples of Osserman algebraic curvature tensors have a typical structure. They can be produced from a metric tensor and a finite set of skew-symmetric matrices which fulfil Clifford commutation relations. We show by means of Young symmetrizers and a theorem of S. A.…
New scoring rules compare probabilistic top lists in classification.
problem Evaluation of probabilistic top lists in classification.
method Elicitability through symmetric proper scoring rules.
result Brier score provides a well-suited metric for comparison.
Paper constructs an example of a non-compact submanifold in a quaternionic Kähler symmetric space.
problem Tackles the construction of a non-compact totally complex submanifold in a quaternionic Kähler symmetric space.
method Uses an isometric action of a compact Lie group and a maximal totally geodesic sphere.
result Proves the existence of a non-compact totally complex submanifold of maximal dimension in a compact quaternionic Kähler symmetric space.
Despite our extensive knowledge of biophysical properties of neurons, there is no commonly accepted algorithmic theory of neuronal function. Here we explore the hypothesis that single-layer neuronal networks perform online symmetric nonnegative matrix factorization (SNMF) of the similarity matrix of the streamed data. …
The flow of a torus by inverse mean curvature keeps total curvature bounded until singularity.
problem Understanding the behavior of a torus under inverse mean curvature flow until singularity.
method Analyzing the evolution of a rotationally symmetric embedded torus in R3 by inverse mean curvature flow. result The total curvature remains bounded until the singular time Tmax. Symmetric CNNs improve sequential recommendation and protein structure prediction.
problem Improving prediction accuracy in sequential recommendation and protein structure inference.
method Developed a CNN architecture that preserves symmetry in convolutional layers, using parameterized convolutional kernels.
result Symmetric structured CNNs achieve better performance with fewer parameters.
Study on surfaces with constant curvature under a specific connection.
problem Classifying surfaces with constant sectional curvature under a semi-symmetric non-metric connection.
method Analyzing surfaces in R3 with a canonical semi-symmetric non-metric connection determined by a vector field. result Classification of surfaces under various conditions (cylindrical, rotational) with constant sectional curvature.
We show that one can skip the skew-symmetry assumption in the definition of Nambu-Poisson brackets. In other words, a n-ary bracket on the algebra of smooth functions which satisfies the Leibniz rule and a n-ary version of the Jacobi identity must be skew-symmetric. A similar result holds for a non-antisymmetric versio…
Using Seiberg-Witten theory, it is shown that any Kaehler metric of constant negative scalar curvature on a compact 4-manifold M minimizes the L^2-norm of scalar curvature among Riemannian metrics compatible with a fixed decomposition H^2(M)=(H^+) + (H^-). This implies, for example, that any such metric on a minimal ru…
R2N learns interpretable rules and literals from numerical features.
problem Lack of expressive vocabulary in rule-based decision models.
method Relational Rule Network (R2N) learns literals and rules end-to-end.
result Learned literals improve prediction accuracy and rule conciseness.
New foundation for Shapley value immune to coalitional manipulations.
problem Coalitional manipulations in game theory.
method Revised Shapley value criteria for coalitional games.
result Shapley value is immune to coalitional manipulations under new criteria.
New framework learns interpretable rule ensembles without sacrificing accuracy.
problem Trade-off between accuracy and interpretability in rule ensembles.
method Introduces local interpretability and a regularizer to promote it, using coordinate descent with local search.
result Learns rule ensembles with fewer rules to explain individual predictions, maintaining comparable accuracy.
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 efficient method for inverse Z-transform reduces complexity significantly.
problem Efficient numerical realization of inverse Z-transform for large n.
method Derives sufficient conditions for new scheme, applies to option pricing.
result Significant reduction in complexity for large n, especially for European options.
DeepCTRL integrates rules into deep learning models, allowing flexible control at inference.
problem Lack of flexibility in incorporating rules into deep learning models.
method Integrates rule representations into deep neural networks, enabling flexible control at inference.
result Improves rule verification ratio and accuracy gains at downstream tasks.
In this article supervised learning problems are solved using soft rule ensembles. We first review the importance sampling learning ensembles (ISLE) approach that is useful for generating hard rules. The soft rules are then obtained with logistic regression from the corresponding hard rules. In order to deal with the p…
New methods prune unpromising rules from KGs, improving scalability and runtime.
problem Scalability issues in walk-based rule learning from KGs.
method Rule Hierarchy Framework (RHF) and Hierarchical Pruning (HPMs).
result Significant reductions in runtime and number of learned rules without compromising predictive performance.
New game approximates mean curvature flow evolution.
problem Approximating geometric mean curvature flow evolution.
method Two-player zero-sum game with probabilistic elements.
result Value function approximates mean curvature flow.
Paper extends transfer learning for decision rules, improving treatment rule estimation.
problem Estimating optimal individualized treatment rules under changing conditions.
method Bayes decision rules and low-dimensional empirical risk minimization.
result Consistent estimators and risk bounds established under mild conditions.
Study explores reinforcement learning in a complex game environment, analyzing rule inference and policy learning.
problem Learning optimal policies in environments with hidden rules.
method Investigated using the Game Of Hidden Rules (GOHR) environment, employing Feature-Centric and Object-Centric state representations with a Transformer-based A2C algorithm.
result Transformer-based A2C models outperform traditional methods in GOHR, demonstrating the effectiveness of representation strategies.
CRL approach improves understanding of heterogeneous treatment effects in complex diseases.
problem Estimating heterogeneous treatment effects in complex diseases.
method Causal rule learning (CRL) workflow consisting of rule discovery, selection, and analysis.
result CRL outperforms other methods in providing interpretable estimates of HTE.
Generative models learn rules at different timescales, revealing a 'innovation window'.
problem Generative models' convergence to empirical training distribution rather than population distribution.
method Rule-valid synthetic tasks, analyzing τrule and τmem across training timescales. result The 'innovation window' widens with increasing dataset size and narrows with rule complexity.
A method for collecting human supervision that combines rules and instance labels.
problem Lack of labeled data and inefficient human supervision.
method Rule-exemplar method with training algorithm for joint denoising and model training.
result Our algorithm is more accurate than existing methods and effectively denoises rules.
Skip connections improve biologically-inspired learning rules.
problem Biologically-inspired learning rules often underperform compared to backpropagation.
method Introduced skip connections between intermediate layers in biologically-motivated learning rules.
result Skip connections can match the performance of backpropagation and are robust to hyper-parameters.
A new learning rule consistently reduces error over data samples.
problem Finding a learning rule that consistently reduces error over all data distributions.
method A deterministic, data-dependent partitioning rule that only partitions cyclic intervals with sufficient empirical diversity of labels.
result The expected error is monotone non-increasing with the sample size under every data distribution.
Advances rule-based multi-label classification using conformal prediction.
problem Improving accuracy and decision making in multi-label classification.
method Combines conformal prediction with rule-based learning to provide natural conformity scores and calibrate rule assessments.
result Calibrated conformity scores enhance prediction accuracy and decision making.
Statistical relational models provide compact encodings of probabilistic dependencies in relational domains, but result in highly intractable graphical models. The goal of lifted inference is to carry out probabilistic inference without needing to reason about each individual separately, by instead treating exchangeabl…
New method for inferring network topology from partial data.
problem Inferring network topology from limited node data.
method Vector autoregressive model and Gaussian mixture algorithm.
result The proposed method converges to the network combination matrix in probability.
A new robust and flexible classification method for non-Gaussian data.
problem Robustness to scale changes and non-Gaussian distributions in classical discriminant analysis.
method FEMDA uses arbitrary Elliptically Symmetrical distributions and scale parameters for each data point.
result FEMDA is robust to scale changes and outperforms other methods.
In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic neurons, resulting in local learning rules. A systematic framework for studying t…
We show that the space of algebraic covariant derivative curvature tensors R' is generated by Young symmetrized tensor products W*U or U*W, where W and U are covariant tensors of order 2 and 3 whose symmetry classes are irreducible and characterized by the following pairs of partitions: {(2),(3)}, {(2),(2 1)} or {(1 1)…
New pivoting strategy improves trace norm contraction in low-rank approximation.
problem Finding good low-rank approximations of symmetric, positive-definite matrices.
method Choosing rows with likelihood proportional to Aii2 for randomly pivoted partial Cholesky algorithm. result Same trace norm contraction result in Frobenius norm for improved pivoting strategy.
Throughout music history, theorists have identified and documented interpretable rules that capture the decisions of composers. This paper asks, "Can a machine behave like a music theorist?" It presents MUS-ROVER, a self-learning system for automatically discovering rules from symbolic music. MUS-ROVER performs feature…