New γ-capsule networks improve adversarial robustness and explainability of capsule networks.
problem Improving the robustness and explainability of capsule networks.
method Introducing γ-capsule networks with a new routing algorithm and training method. result Experimental results show γ-capsule networks are more robust and transparent. Study proposes a more accurate method for classifying transposable elements.
problem Classifying transposable elements for understanding their genetic and evolutionary effects.
method Utilized Support Vector Machines (SVM) for hierarchical classification of transposable elements.
result Proposed a robust approach for hierarchical classification of transposable elements with higher accuracy.
We consider the problem of accurately estimating the reliability of workers based on noisy labels they provide, which is a fundamental question in crowdsourcing. We propose a novel lower bound on the minimax estimation error which applies to any estimation procedure. We further propose Triangular Estimation (TE), an al…
Normal forms found for meromorphic connections over a specific F-manifold.
problem Characterizing meromorphic connections over a specific F-manifold.
method Finding normal forms for Euler fields and meromorphic connections.
result Characterized Euler fields induced by (TE)-structures. Investor flows in Korean equity market transmit shared information, not private signals.
problem Whether investor flows transmit private information or only public signals.
method Transfer Entropy networks constructed from investor-type flows over
umNDates{} trading days.
result Investor flows transmit shared information, not private signals.
Proposes a new VAE model to estimate treatment effects from confounded data.
problem Estimating treatment effects in the presence of confounding variables.
method Intact-VAE, a variant of variational autoencoder (VAE), using a latent variable for confounders.
result Proves identification of treatment effects under unconfoundedness and shows state-of-the-art performance.
Unified framework maps financial market dynamics using TE and KM, revealing directional information flow.
problem Challenges in traditional correlation analysis of financial markets, especially during crises.
method Combines Transfer Entropy (TE) and Kramers-Moyal (KM) expansion to analyze dynamic interactions among major indices.
result Increased directional information flow during crises, highlighting gold-dollar and oil-equity linkages.
Paper proposes a method to estimate Transfer Entropy using Copula Entropy.
problem Estimating Transfer Entropy for causal discovery.
method Non-parametric method based on Copula Entropy.
result The proposed method effectively infers causality relationships from data.
New method tackles OOD robustness with a single additional variable.
problem Out-of-distribution generalization with unobserved confounders.
method Identifiability assumptions using a single additional variable.
result Superior empirical performance on benchmark tasks.
TES optimizes black-box functions efficiently with minimal approximations.
problem Efficient Bayesian optimization with minimal approximations and generalization to batch BO.
method TES acquisition function measures information gain on trusted maximizers.
result TES achieves state-of-the-art performance with minimal approximations.
A new VAE model identifies and estimates treatment effects with limited overlap.
problem Identifying and estimating treatment effects when subjects with certain features belong to a single treatment group.
method Developed a latent variable model to estimate a prognostic score, which is sufficient for treatment effects. The model is a new type of VAE called β-Intact-VAE.
result The model identifies individualized treatment effects and provides TE error bounds.
In this note we prove that, for a vector bundle E over a manifold M, a Dorfman bracket on TM⊕E∗ anchored by prTM and with E a vector bundle over M, is equivalent to a lift from Γ(TM⊕E∗) to linear sections of TE⊕T∗E→E, that intertwines the given Dorfman bracket w…
EPSTE: A geometric token and deep learning approach to estimating transfer entropy in neuroimaging time series
problem Inferring directed interactions between neural systems from EEG and MEG
method Reframing TE estimation as a learnable problem operating on structured symbolic representations
result EPSTE achieves near-perfect recovery of ground-truth directed structure and significantly lower absolute error than the baseline
Let X be a simply connected 4-manifold containing a (−1)-sphere e. Fintushel and Stern prove that Dc(exp(te))=Dc(B(t))one⊥ifc⋅eiseven, Dc(exp(te))=Dc−e(S(t))one⊥ifc⋅eisodd, for some universal series $B(t),S(t) \in \Q[x][[t]]$ with x the class of a point. …
A (TE)-structure ∇ over a complex manifold M is a meromorphic connection defined on a holomorphic vector bundle over C×M, with poles of Poincaré rank one along {0}×M. Under a mild additional condition (the so called unfolding condition), ∇ induces a multiplication on TM…
Proposes a new method to adapt to covariate shifts in supervised learning.
problem Covariate shift in training and testing samples with different marginal distributions.
method Minimax risk classification (MRC) approach that weights both training and testing samples.
result Significantly enhanced classification performance in synthetic and empirical experiments.
The aim of these notes is to relate covariant stochastic integration in a vector bundle E (as in Norris \cite{Norris}) with the usual Stratonovich calculus via the connector $\K:TE \rightarrow E$ (cf. e.g. Paterson \cite{Paterson} or Poor \cite{Poor}) which carries the connection dependence.
New insights into overfitting peaks in generalization error for l2 and l1 penalized interpolation.
problem Understanding the phenomenon of overfitting peaks in generalization error for modern machine learning models.
method Introducing a generative and fitting model pair (MiSpaR) and deriving analytical risk curves for l2 and l1 penalties. result The overfitting peak can be dissociated from the point of model flexibility, complicating the interpretation of overfitting as a boundary between classical and modern regimes.
Quantum computing improves fault diagnosis in industrial processes.
problem Fault detection and diagnosis in industrial process systems.
method Integrates quantum computing and deep learning to extract features and diagnose faults.
result Quantum-assisted deep learning achieves high fault detection rates (79.2% and 99.39%).
The paper linearizes higher Courant algebroids using jet and differential operators.
problem Understanding the structure of higher Courant algebroids.
method Isomorphic spaces of sections and linearization of jet and differential operator bundles.
result Higher Courant algebroids can be linearized as pseudo-linearization and Weinstein-linearization.
TES-AE uses tree grammars to speed up autoencoding for tree data.
problem Challenges in autoencoding tree data due to its non-vectorial and discrete nature.
method TES-AE combines reservoir computing with tree grammars for faster training.
result TES-AE outperforms D-VAE in speed and accuracy for tree data.
A new method models continuous-time counterfactual outcomes using neural controlled differential equations.
problem Estimating personalized healthcare outcomes over irregularly sampled data.
method Interpreting data as samples from a continuous-time process, modeling latent trajectory using controlled differential equations, and using adversarial training for time-dependent confounding.
result TE-CDE consistently outperforms existing approaches in irregularly sampled scenarios.
We consider a simple investment project with the following parameters: I>0: Initial investment which is amortizable in n years; n: Number of years the investment allows production with constant output per year; A>0: Annual amortization (A=I/n); Q>0: Quantity of products sold per year; Cv>0: Variable cost per unit; p>0:…
Neuron Shapley identifies key neurons in deep networks, improving model accuracy and fairness.
problem Identifying responsible neurons in deep networks for better model performance and fairness.
method Neuron Shapley framework quantifies neuron contributions, accounting for interactions.
result Removing just 30 critical filters can destroy model accuracy, revealing network function.
Describes explaining neurons in deep representations using compositional logical concepts.
problem Interpreting neuron behavior in deep neural networks.
method Identifying compositional logical concepts that closely approximate neuron behavior.
result Compositional explanations provide insights into model performance and allow for adversarial example creation.
SeReNe prunes neurons with low sensitivity to reduce network size.
problem Large neural networks consume too many resources on resource-constrained devices.
method Exploits neural sensitivity as a regularizer to prune neurons with low sensitivity.
result Pruning neurons with low sensitivity achieves competitive compression ratios.
Under-parameterized networks can either copy or average teacher weights, leading to universal optimal solutions.
problem Approximating a teacher network with an under-parameterized student network.
method Analyzing shallow neural networks with erf activation function and unitary teacher weights, proving copy-average configurations are critical points and finding the optimal solution.
result The optimal solution for under-parameterized networks has a universal structure, whether copying or averaging teacher neurons.
We define Dorfman connections, which are to Courant algebroids what connections are to Lie algebroids. Several examples illustrate this analogy. A linear connection ∇:X(M)×Γ(E)→Γ(E) on a vector bundle E over a smooth manifold M is tantamount to a linear splitting $TE\simeq T^{q_E}E\op…
This research investigates selectively pruning hyper and hypo neurons to improve neural network generalization.
problem Improving neural network generalization to unseen data.
method Investigates pruning hyper and hypo neurons selectively in fully connected layers of CNNs.
result Selective pruning of hyper and hypo neurons improves model performance on out-of-domain data.
Modeling hidden neurons in SNNs using mesoscopic approximations.
problem Underconstrained problem of modeling unobserved neurons in SNNs.
method Coarse-graining and mean-field approximations to derive neuLVM.
result neuLVM can efficiently model large SNNs and recover connectivity parameters.
Topological methods improve neuron analysis and tracer injection summary.
problem Traditional methods fail to capture the tree-like structure of neurons.
method Discrete Morse (DM) Theory for neuron skeletonization and consensus tree summarization.
result Significant performance improvements over non-topological methods.
We propose a new generic type of stochastic neurons, called q-neurons, that considers activation functions based on Jackson's q-derivatives with stochastic parameters q. Our generalization of neural network architectures with q-neurons is shown to be both scalable and very easy to implement. We demonstrate expe…
Quadratic autoencoder improves low-dose CT image denoising.
problem Low-dose CT image denoising.
method Quadratic autoencoder architecture applied to CT denoising.
result Quadratic autoencoder achieves superior denoising performance and efficiency.
BEAN models neuronal correlations to create interpretable representations.
problem Hard interpretation of dense-layer representations in DNNs.
method Inspired by neuroscience, BEAN models neuronal correlations and dependencies.
result BEAN enables formation of interpretable neuronal clusters without sacrificing model performance.
SpaRCe optimizes reservoir computing by learning neuron thresholds to improve performance and prevent forgetting.
problem Improving performance and preventing forgetting in reservoir computing networks.
method Integrates neuron-specific learnable thresholds to optimize sparsity without altering dynamics, learning read-out weights and thresholds via gradient rule.
result Threshold learning improves performance and alleviates catastrophic forgetting.
It will be shown that according to theorems of K. Menger, every neuron grid if identified with a curve is able to preserve the adopted qualitative structure of a data space. Furthermore, if this identification is made, the neuron grid structure can always be mapped to a subset of a universal neuron grid which is constr…
This work improves DNN interpretability by reducing neuron ambiguity.
problem Lack of interpretability in DNNs, especially in healthcare applications.
method Developed a metric to evaluate neuron consistency, used adversarial examples to identify ambiguous features, and proposed adversarial training to improve consistency.
result Reduced ambiguity of neurons in DNNs, improving interpretability.
A new method to understand neural networks by sampling the 'inverse set' of a neuron.
problem Understanding the internal representation of neurons in neural networks.
method Optimization-based sampling approach to characterize the input space that excites a neuron.
result Inspection of samples reveals regularities that help understand the neuron's representation.
Neural networks learn to mimic brain neurons with two-input activation functions, improving performance and robustness.
problem Training neural networks to mimic the complex interactions of brain neurons.
method Developed a network-in-network architecture with two-input activation functions, optimized hyperparameters, and compared to conventional ReLU networks.
result Two-input activation functions can learn soft XOR functions, improving network performance and robustness.
CHANI learns classification tasks with local transformations inspired by biology.
problem Proving neural networks can learn classification tasks with local transformations.
method CHANI uses spiking neurons modeled by Hawkes processes with expert aggregation for local learning.
result CHANI can learn and encode multiple classes, forming assemblies of neurons.
Researchers develop methods to learn neuron dynamics from colored noise.
problem Learning nonlocal stochastic neuron dynamics from colored noise.
method Proposed two methods for closing Fokker-Planck equations: nonlocal large-eddy-diffusivity closure and data-driven sparse regression.
result Mutual information and total correlation between stimulus and neuron states calculated for FHN neuron.
Single neuron with ADA learns XOR and outperforms other functions.
problem Classifying linearly non-separable data.
method Proposed a new artificial neuron with apical dendrite activation.
result ADA function achieves 100% accuracy on XOR and superior performance on benchmark datasets.
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. …
Stable unactivated neurons reduce expressiveness in ReLU networks.
problem Reducing expressiveness in ReLU neural networks due to stably unactivated neurons.
method Investigated the probability of neurons being stably unactivated in ReLU networks with symmetric weight and bias distributions.
result Proved the probability of a neuron being stably unactivated in the second hidden layer of a ReLU network.
Novel chaotic neurons improve AI with minimal training data.
problem Limited training data for AI algorithms.
method Intrinsically chaotic neurons inspired by chaos theory.
result Classification accuracy up to 95.8% with just 2 training samples per class.
Single-spike neurons can approximate as well as multi-spike neurons.
problem Limitation of single-spike neurons in spiking neural networks.
method Comparison of single-spike and multi-spike neural networks.
result Single-spike and multi-spike neural networks are equivalent in approximation capabilities.
The challenge of assigning importance to individual neurons in a network is of interest when interpreting deep learning models. In recent work, Dhamdhere et al. proposed Total Conductance, a "natural refinement of Integrated Gradients" for attributing importance to internal neurons. Unfortunately, the authors found tha…
Optimal neuron activation functions improve neural network performance.
problem Limited expressive power of standard neuron activation functions in neural networks.
method Additive Gaussian process regression to construct individual neuron activation functions.
result Optimal neuron activation functions lead to better performance and reduced overfitting.