The study analyzes neural interactions using an Ising model to reveal contributions of pairwise interactions to sparseness and fluctuation.
problem Understanding the contributions of pairwise interactions to sparseness and fluctuation in neural activity.
method Inference methods for a time-dependent Ising model to analyze neural interactions and estimate time-dependent neural interactions with credible intervals.
result Pairwise interactions contribute to increasing sparseness and fluctuation in neural activity.
Rotation-equivariant CNN reveals common features in V1 neurons.
problem V1 models fail to predict natural stimuli responses accurately.
method Rotation-equivariant convolutional neural network model.
result Rotation-equivariant network outperforms regular CNN and reveals common features.
This paper presents a Bayesian approach to learning the connectivity structure of a group of neurons from data on configuration frequencies. A major objective of the research is to provide statistical tools for detecting changes in firing patterns with changing stimuli. Our framework is not restricted to the well-under…
Study finds many stocks in S&P 500 are inefficient, suggesting financial analysts outperform blindfolded monkeys.
problem Degree of inefficiency in U.S. stock market performance.
method Confidence intervals for proportions to assess inefficiency in S&P 500 components.
result Proportion of inefficient stocks in the S&P 500 index estimated to be between 12.13% and 27.87%
New model explains visual illusions using sub-Riemannian geometry.
problem Mathematical modeling of Poggendorff-type visual illusions.
method Cortical-inspired sub-Riemannian model with sub-Laplacian evolution.
result Sub-Riemannian kernel enhances visual misperceptions and biases.
Experiments that study neural encoding of stimuli at the level of individual neurons typically choose a small set of features present in the world --- contrast and luminance for vision, pitch and intensity for sound --- and assemble a stimulus set that systematically varies along these dimensions. Subsequent analysis o…
Unified framework models neural decision-making, improving accuracy.
problem Limitations in modeling neural activity during decision-making.
method Unifying framework based on state-space models with scalable inference.
result Two-dimensional accumulator better captures neural responses.
A new model of V1 using orientation, frequency, and phase.
problem Understanding the complex behavior of V1 simple cells.
method Developed a sub-Riemannian model based on Gabor functions.
result The model enhances images using orientation, frequency, and phase.
Neurons in higher cortical areas, such as the prefrontal cortex, are known to be tuned to a variety of sensory and motor variables. The resulting diversity of neural tuning often obscures the represented information. Here we introduce a novel dimensionality reduction technique, demixed principal component analysis (dPC…
Model captures context-dependent neural correlations using Poisson mixtures.
problem Capturing context-dependent noise correlations in neural populations.
method Conditional finite mixtures of Poisson distributions, cross-validation for dimensionality, EM algorithm.
result Model successfully captures stimulus-dependent correlations in V1 neuron responses.
V1 cortex reconstructs images as Poisson equation solutions with varying weights.
problem Reconstructing images from V1 cortical cell receptive profiles.
method Solves a heterogeneous Poisson equation with varying weights representing neural connectivity.
result Reconstructions converge to homogeneous solutions using homogenization techniques.
Adds a precortical module to CNNs for improved robustness to light variations.
problem Robustness of CNNs to global light intensity and contrast variations.
method Developed a mathematical model of the mammalian visual pathway, inspired by CNNs, and added a preliminary convolutional module.
result Significantly more robust CNNs achieved with added module on MNIST, FashionMNIST, and SVHN databases.
A new geometric model for V1 hypercolumns combines symplectic and spherical models.
problem Understanding the structure of V1 hypercolumns in the visual cortex.
method A differential geometric model based on conformal geometry.
result Combines features of symplectic and spherical models of hypercolumns.
New estimator corrects bias in CKA for sparsely sampled neurons.
problem Bias in CKA for sparsely sampled neurons.
method Novel estimator that corrects for input and feature sampling.
result Reliable model-to-brain alignment with sparsely sampled neurons.
The ECME algorithm has proven to be an effective way of accelerating the EM algorithm for many problems. Recognising the limitation of using prefixed acceleration subspace in ECME, we propose the new Dynamic ECME (DECME) algorithm which allows the acceleration subspace to be chosen dynamically. Our investigation of an …
New method MRI improves machine learning models' ability to generalize to unseen data.
problem Machine learning models often fail to generalize well to out-of-distribution data.
method Introduces a new notion of invariance (MRI) and a practical version (MRI-v1) to improve model generalization.
result MRI-v1 guarantees invariant predictors and outperforms IRM-v1 in various settings.
The paper proposes a model to learn motion perception in V1 using vector and matrix representations.
problem Motion perception in primary visual cortex (V1).
method Coupling vector representations of local contents and matrix representations of local pixel displacements.
result The model can learn Gabor-like filter pairs and infer local motions.
DeepPeep attacks DNN architectures to reveal design details, posing IP theft risks.
problem Protecting DNN architecture from IP theft in cloud-based services.
method Two-stage attack methodology exploiting design characteristics.
result DeepPeep successfully reverses-engineers compact DNN architectures.
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 …
For a company looking to provide delightful user experiences, it is of paramount importance to take care of any customer issues. This paper proposes COTA, a system to improve speed and reliability of customer support for end users through automated ticket classification and answers selection for support representatives…
Bayesian model predicts iron deficiency from multi-source multi-way molecular data.
problem Predicting iron deficiency in rhesus monkeys from multi-source multi-way molecular data.
method Developed a Bayesian approach with a linear model incorporating multi-way dependence and varying signal sizes across sources.
result Model accurately classifies iron deficiency in monkeys and outperforms simpler models.
The edges of torn plastic sheets and growing leaves often display hierarchical buckling patterns. We show that this complex morphology (i) emerges even in zero strain configurations, and (ii) is driven by a competition between the two principal curvatures, rather than between bending and stretching. We identify the key…
MeliusNet improves binary neural networks to match MobileNet-v1 accuracy.
problem Achieving high accuracy with binary neural networks on mobile devices.
method Alternating DenseBlocks and ImprovementBlocks to increase feature capacity and quality.
result MeliusNet matches MobileNet-v1 accuracy on ImageNet, improving binary network performance.
In this paper, we study the classification problem in which we have access to easily obtainable surrogate for true labels, namely complementary labels, which specify classes that observations do \textbf{not} belong to. Let Y and Yˉ be the true and complementary labels, respectively. We first model the annotati…
A model predicts visual motion by learning from natural videos.
problem Temporal prediction accuracy in visual perception.
method Self-supervised representation learning using Fourier shift theorem.
result Achieves better prediction performance than traditional methods.
When governed by underlying low-dimensional dynamics, the interdependence of simultaneously recorded population of neurons can be explained by a small number of shared factors, or a low-dimensional trajectory. Recovering these latent trajectories, particularly from single-trial population recordings, may help us unders…
HIVE-COTE v1.0 improves time series classification with enhanced usability.
problem Improving time series classification accuracy and usability.
method Presented a walkthrough guide and extensive experimental evaluation of HIVE-COTE v1.0.
result HIVE-COTE v1.0 outperforms three recently proposed algorithms in predictive performance and resource usage.
PLS-Lasso integrates dimension reduction into regression for financial index tracking.
problem Dimension reduction and regression are traditionally treated separately in multivariate data analysis.
method PLS-Lasso integrates dimension reduction directly into the regression process, presenting two formulations: PLS-Lasso-v1 and PLS-Lasso-v2.
result PLS-Lasso-v1 and PLS-Lasso-v2 outperform Lasso in financial index tracking.
In math.DG/9903083 (henceforth referred to as EA) we defined an integer invariant h(Y) for oriented integral homology 3-spheres Y which only depends on the rational homology cobordism class of Y and is additive under connected sums. In this paper we establish lower bounds for h(Y) when Y is the boundary of a …
In this paper a method for the resolution of the differential equation of the Jacobi vector fields in the manifold V1 = Sp(2)/SU(2) is exposed. These results are applied to determine areas and volumes of geodesic spheres and balls.
Polymarket-v1 Database tracks 1.2B trades across 1.3M markets with 100% ground-truth direction.
problem Lack of ground-truth data in prediction markets archives.
method Ground-truth archive of 1.2B trades from Polymarket's CTF Exchange.
result Ground-truth data reveals systematic errors in microstructure metrics.
SeizureNet classifies EEG seizures with high accuracy.
problem Challenges in classifying epileptic seizures due to signal quality and patient variability.
method Deep learning framework using multi-spectral feature embeddings and knowledge distillation.
result SeizureNet achieves high F1 scores for seizure and patient-wise classification.
Let M be a compact irreducible hyperkahler manifold, from Bogomolov inequality [V1] we obtain forbidden values of the second Betti number b2 in arbitrary dimension. UPD: Unfortunately, decomposition of dual to BBF-form is not right in the main theorem. Instead of this work, take a look on recent preprints of Sawon…
Although Generative Adversarial Networks (GANs) have shown remarkable success in various tasks, they still face challenges in generating high quality images. In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images. First, we propose a two-…
Paper benchmarks machine learning for multi-class seizure type classification.
problem Accurate classification of seizure types in epileptic patients.
method Used machine learning algorithms on the TUH EEG seizure corpus.
result Achieved weighted F1 scores of up to 0.901 for seizure-wise cross validation. New model for visual cortex border completion using bicycle wheel motions.
problem Understanding border completion in the visual cortex V1.
method Sub-Riemannian Hamiltonian formalism and bicycle wheel analogy.
result Analogies between visual cortex border completion and bicycle wheel motions.
Two new algorithms speed up TreeSHAP computation for tree-based models.
problem Slow computation of SHAP values on tree-based models.
method Two new algorithms, Fast TreeSHAP v1 and v2, designed to improve computational efficiency.
result Fast TreeSHAP v2 is 2.5x faster than TreeSHAP, with slightly higher memory usage.
A new method quantizes neural networks to low-precision without STE, improving accuracy.
problem Quantization of neural networks to low-precision without a complete theoretical understanding.
method Alpha-blending (AB) using stochastic gradient descent (SGD) to quantize weights and gradually increase the coefficient α. result Improves top-1 accuracy by 0.9% on 1-bit BinaryNet, 0.82% on 8-bit MobileNet v1, and 2.93% on 4-bit ResNet_50 v1/2 compared to STE.
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.
Adversarial Robustness Toolbox (ART) is a Python library supporting developers and researchers in defending Machine Learning models (Deep Neural Networks, Gradient Boosted Decision Trees, Support Vector Machines, Random Forests, Logistic Regression, Gaussian Processes, Decision Trees, Scikit-learn Pipelines, etc.) agai…
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.
Random investment strategies outperform sensible ones, even with forecasts.
problem The usefulness of investment strategies based on forecasts is questioned.
method Investigated the performance of sensible and nonsensical investment strategies, including forecasts.
result There is no substantial difference between the performances of ``best'' and ``trivial'' forecasts.
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.
A simple DQN-based multi-agent RL system for binary actions.
problem Complexity and training issues in multi-agent reinforcement learning.
method Shared state and rewards, agent-specific actions, experience replay pool.
result Better performance and faster convergence compared to conventional methods.