Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,786 papers · 148 categories

Trend · papers per month

25.0%50.0%75.0%100.0% · Sep 199219922001200920172026
48 results for class activation mapping

The paper proves deep neural networks with analytic activation can approximate any function.

problem Approximating functions with neural networks using analytic activation functions.
method Elementary proofs for real and complex networks, Stone-Weierstrass theorem, Mergelyan's theorem.
result Closure of neural network classes equals space of polynomials for analytic activation.

Improved generalization bounds for CNNs using Rademacher complexity.

problem Establishing non-vacuous generalization bounds for deep learning models.
method Rademacher complexity framework with novel contraction lemmas for high-dimensional mappings.
result Enhanced generalization bounds for a broader class of activation functions.

Traditional human activity recognition (HAR) based on time series adopts sliding window analysis method. This method faces the multi-class window problem which mistakenly labels different classes of sampling points within a window as a class. In this paper, a HAR algorithm based on U-Net is proposed to perform activity…

2018-09-20abs ↗pdf ↗

Visualizes deep neural networks for speech recognition using learned topographic filter maps.

problem Unintuitive internal structure of deep neural networks complicates activation visualization.
method Trains a convolutional speech recognition model with filters arranged in a 2D grid, highlighting similar filters.
result Topographic filter maps visualize artificial neuron activations more intuitively.

This paper classifies typhoon damage features using aerial photography.

problem Typhoon damages and slow recovery times.
method Aerial photography for classification of eight classes including land covers and disaster areas.
result Visualize and explain typhoon disaster features using convolutional activation maps.

Study embeddings between Barron spaces with various activation functions, focusing on RePU.

problem Understanding the influence of activation functions on infinitely wide neural networks.
method Prove embeddings by constructing push-forward maps on measures representing functions.
result Barron spaces with RePU activation have a hierarchical structure similar to Sobolev spaces.

We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing input regions that are 'important' for predictions -- or visual explanations. Our approach, called Gradient-weighted Class Activation Mapping (Grad-CAM), uses class-specific gradient information to localize…

2016-11-22abs ↗pdf ↗

AReLU uses attention-based rectification to improve neural network performance.

problem Improving neural network performance through better activation functions.
method Integrates attention mechanism with rectified linear unit (ReLU) to learn and scale feature maps.
result AReLU significantly boosts performance of most network architectures with minimal changes.

Balanced Activation improves object detection performance on long-tailed datasets.

problem Mismatch between training and testing label distributions in object detection.
method Introduces Balanced Activation (Balanced Softmax and Balanced Sigmoid) to address label distribution shift.
result Balanced Activation provides ~3% gain in mAP on LVIS-1.0 compared to state-of-the-art methods.

Improved EXACT strategy reduces GNN memory consumption and runtime.

problem Efficiently training large-scale GNNs with reduced memory usage.
method Block-wise quantization of intermediate activation maps with improved variance minimization.
result Further reduction in memory consumption (>15%) and runtime speedup (5%) with similar performance trade-offs.

First the title could be also understood as ``3-manifolds related by non-zero degree maps" or "Degrees of maps between 3-manifolds" for some aspects in this survey talk. The topology of surfaces was completely understood at the end of 19th century, but maps between surfaces kept to be an active topic in the 20th centur…

2003-04-21abs ↗pdf ↗

Framework tackles class imbalance and noisy labels in active learning.

problem Class imbalance and noisy labels in real-world datasets.
method Uses foundation model priors to select informative samples for active learning.
result Substantial annotation savings (over 50%) with preserved performance and robustness.

ActiLabel learns activity patterns across diverse sensor devices.

problem Limited adoption of activity recognition models across different domains due to diverse sensor devices.
method Combination of graph model and optimal tiered mapping for learning activity labels.
result Superior performance compared to state-of-the-art methods on public datasets.

We consider active maximum a posteriori (MAP) inference problem for Hidden Markov Models (HMM), where, given an initial MAP estimate of the hidden sequence, we select to label certain states in the sequence to improve the estimation accuracy of the remaining states. We develop an analytical approach to this problem for…

2014-11-03abs ↗pdf ↗

Active learning reduces simulation needs for high-fidelity mobility maps.

problem Efficiently training machine learning classifiers for high-fidelity mobility maps.
method Active learning based on PAC learning theory to reduce simulation needs.
result Our sampling algorithm trains neural networks with higher accuracy using less than half the number of simulations.

CBDA improves active learning for semantic segmentation, especially with imbalanced classes.

problem Class imbalance degrades performance in domain adaptive active learning.
method Class Balanced Dynamic Acquisition (CBDA) selects more balanced labels for active learning.
result CBDA increases minority class performance and outperforms baselines by 0.6-2.4 mIoU.

SympNets identify Hamiltonian systems from data using linear, activation, and gradient modules.

problem Identifying Hamiltonian systems from data.
method Composition of linear, activation, and gradient modules; universal approximation theorems.
result SympNets can approximate arbitrary symplectic maps and generalize well to various Hamiltonian systems.

Universal approximation for ODENet and ResNet with a single activation function.

problem Approximating complex dynamical systems with limited vector fields.
method Examined ODENet and ResNet with vector fields composed of a single activation function and affine mapping.
result ODENet and ResNet with restricted vector fields can uniformly approximate those with general vector fields.

Generalizes neural networks for infinite-dimensional mappings, including PDE solutions.

problem Learning mappings between infinite-dimensional spaces and finite-dimensional approximations.
method Graph kernel network architecture with message passing for kernel integration.
result Competitive performance compared to state-of-the-art solvers for PDEs.

Softmax cross-entropy optimizes mutual information in neural networks.

problem Understanding the relationship between mutual information and classification neural networks.
method Demonstrated that optimizing softmax cross-entropy maximizes mutual information between inputs and labels.
result Softmax cross-entropy can approximate mutual information and highlight relevant image regions.

Transformers exhibit sparse activation maps, reducing computational load and improving robustness.

problem Sparse activation in Transformer models.
method Extensive experiments on various Transformer architectures and tasks.
result Sparsity in Transformers is a prevalent phenomenon, reducing FLOP count and improving model robustness.

GPMI method interpolates uncertain atrial conduction velocity on non-Euclidean manifolds.

problem Uncertainty in atrial conduction velocity calculations.
method Gaussian Process Manifold Interpolation (GPMI) on human atrial manifolds.
result GPMI accounts for atrial topology and calculates CV uncertainty.

O-MedAL optimizes medical image analysis with online active deep learning.

problem Improving accuracy in medical image analysis with limited labeled data.
method Online Active Deep Learning method that queries examples maximizing average distance to training set.
result Significant performance improvements, including 6.30% accuracy boost with 25% labeled data.

Researchers use operator learning to predict cardiac activation and repolarization times.

problem Computational demands and need for clear, interpretable information in cardiac electrophysiology.
method Exploiting Fourier Neural Operators (FNO) and Kernel Operator Learning (KOL) to learn operator mappings.
result Both FNO and KOL approaches are computationally efficient and robust to hyperparameters.

Many neural network architectures rely on the choice of the activation function for each hidden layer. Given the activation function, the neural network is trained over the bias and the weight parameters. The bias catches the center of the activation, and the weights capture the scale. Here we propose to train the netw…

2019-01-28abs ↗pdf ↗

Study evaluates deep learning models for solar flare prediction with interpretability analysis.

problem Lack of interpretability in deep learning models for solar flare prediction.
method Proximity-based metric for analyzing attribution maps generated by Guided Grad-CAM.
result Models' predictions align with active region characteristics, offering insights into their behavior.

The paper studies how neural networks evolve representations, finding a unique fixed point for nonlinear activations.

problem Understanding how neural networks transform input data across layers.
method Theoretical framework for the evolution of the kernel sequence, using mean-field regime and Hermite polynomials.
result For nonlinear activations, the kernel sequence converges globally to a unique fixed point.

New active learning framework for multiclass classification beyond realizability assumption.

problem Active learning in non-realizable settings with convex model classes.
method Surrogate risk minimization, epoch-based fitting, aggregation of models.
result Achieves label and sample complexity comparable to prior work in non-realizable settings.

Improves Active Learning by considering class imbalance and difficulty.

problem Active Learning's focus on individual samples ignores class distribution and difficulty.
method Proposes a method based on Bayes' rule to incorporate class imbalance, using a Variational Auto Encoder (VAE).
result Significantly outperforms state-of-the-art methods on datasets with heavy data imbalance.