Method analyzes deep neural network activations to explain adversarial examples.
problem Difficulty in interpreting deep neural network representations.
method Persistent homology over graphical activation structure.
result Adversarial examples are not semantic structure additions but dominant activation structure alterations.
Analyzes changes in cryptocurrency market structure.
problem Understanding shifts in cryptocurrency market dynamics.
method Structural change analysis techniques.
result Identifies key structural changes in the market.
Improved video tracking accuracy with active learning.
problem Efficiently predicting object matches in videos with active learning.
method Adversarial approach for active learning with structured prediction domains.
result Better accuracy and computational efficiency for object tracking.
Paper analyzes neural networks using active subspace for structural analysis and vulnerability, reducing model size and improving attacks.
problem Analyzing and reducing the complexity of neural networks.
method Active subspace method for measuring active neurons, network structure modification, and additive universal adversarial attack vector.
result ASNet achieves significant parameter and flops reduction, and improves universal adversarial attack performance.
Study reveals geometric properties of neural network activation spaces.
problem Understanding the geometric structure of neural network activation spaces.
method Efficient approximation algorithm to characterize convex hull of activation spaces.
result Four common geometric properties of activation spaces are concluded.
Paper simplifies ANN structure into a functional form.
problem Current ANN structure is complex and difficult to analyze.
method Uses activation integral concept to represent ANN structure as a function.
result Simplified mathematical representation of ANN structure.
Interactive learning framework for various settings.
problem Various interactive learning settings.
method Adapted active learning algorithm for interactive structure discovery.
result Noise-tolerant algorithm with favorable query complexity.
Incremental methods for structure learning of pairwise Markov random fields (MRFs), such as grafting, improve scalability by avoiding inference over the entire feature space in each optimization step. Instead, inference is performed over an incrementally grown active set of features. In this paper, we address key compu…
A new framework scales active search for large datasets.
problem Scaling active search for large, high-dimensional data sets.
method Hierarchical Batch Bandit Search (HBBS) framework.
result HBBS improves performance and scalability for batch search.
Study on online learning with networked agents, showing how network structure affects performance.
problem Understanding how network structure impacts performance in online learning settings.
method Characterized the effect of network structure on regret in both stochastic and adversarial settings.
result Optimal regret bound of order α T \sqrt{αT} α T when activations are stochastic and network structure is known. Risk-based active learning improves SHM decision-making.
problem Lack of prior labels for structural health monitoring.
method Risk-based active learning approach to guide data labeling.
result Improves decision-maker's performance in SHM.
Bayesian optimization selects experiments for causal structure learning in Gaussian process networks.
problem Discover causal relationships in non-linear systems with continuous variables.
method Bayesian active learning and Gaussian process priors combined with Bayesian optimization for experiment selection.
result Efficiently maximizes expected information gain in learning causal structure.
Paper proposes active learning for structured output design, improving Gaussian process model predictions.
problem Finding optimal input parameters for achieving desired structured outputs.
method Developed new acquisition functions to minimize prediction error of Gaussian process model, incorporating output correlations.
result Effectiveness demonstrated in synthetic and real data experiments, including materials informatics.
LASER compresses recursive model activations by exploiting their low-dimensional structure.
problem Understanding and optimizing the geometric structure of recursive reasoning trajectories.
method Dynamic low-rank basis tracking via matrix-free subspace tracking with a fidelity-triggered reset mechanism.
result Recursive activations occupy a linear, low-dimensional subspace that can be compressed efficiently.
Semi-supervised learning improves QSAR model predictions for novel compounds.
problem Improving model predictions for compounds not in the training set and adjusting for selection bias.
method Semi-supervised learning framework to estimate model quality and adjust for selection bias.
result Predictions for novel compounds are improved by accounting for compound similarity and selection bias.
While neural networks are powerful approximators used to classify or embed data into lower dimensional spaces, they are often regarded as black boxes with uninterpretable features. Here we propose Graph Spectral Regularization for making hidden layers more interpretable without significantly impacting performance on th…
Develops a framework to analyze financial structures.
problem Difficulty in systematic analysis, comparison, and verification of financial structures.
method Formalizes financial structures as structured allocation systems with explicit allocation operators.
result Specifies inputs, structural requirements, and feasibility restrictions for financial structures.
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.
New algorithm learns Bayesian network structures with fewer samples.
problem Learning Bayesian network structures with limited observational data.
method Active sampling strategy to select variables for observation.
result Active algorithm finds structures close to optimal with fewer samples.
Complex activity recognition is challenging due to the inherent uncertainty and diversity of performing a complex activity. Normally, each instance of a complex activity has its own configuration of atomic actions and their temporal dependencies. We propose in this paper an atomic action-based Bayesian model that const…
SANs use sparse activation functions to compress data representations.
problem Learning meaningful features without considering compression.
method Introduce φ metric, define activation functions, and present SANs.
result SANs achieve small description length and interpretable kernels.
To compare entities of differing types and structural components, the artificial neural network paradigm was used to cross-compare structural components between heterogeneous documents. Trainable weighted structural components were input into machine-learned activation functions of the neurons. The model was used for m…
Flexible VHDL design for multiple neural networks on FPGAs.
problem Inflexible neural network designs for FPGAs.
method Proposes a flexible VHDL structure with multiple processor groups.
result Allows training and testing of multiple neural networks on multiple FPGAs.
IMPACT optimizes LLM compression by focusing on activation importance, reducing model size up to 55.4%.
problem Resource constraints in deploying large language models (LLMs).
method IMPACT integrates activation importance into low-rank compression, optimizing for both size and accuracy.
result IMPACT achieves up to 55.4% greater model size reduction while maintaining comparable or better accuracy.
A new MARL framework for community-based cooperation with transfer and active exploration.
problem Flexible coordination patterns in multi-agent systems with community structures.
method Community-based multi-agent reinforcement learning with transfer and active exploration.
result Provably convergent actor-critic algorithms for structured information sharing and transfer learning.
SANs use sparse activation functions to minimize model complexity.
problem Model complexity in unsupervised learning.
method Introduce φ metric, define activation functions, present Sparsely Activated Networks (SANs).
result SANs with selected activation functions have small description length and interpretable kernels.
We study the localization of a cluster of activated vertices in a graph, from adaptively designed compressive measurements. We propose a hierarchical partitioning of the graph that groups the activated vertices into few partitions, so that a top-down sensing procedure can identify these partitions, and hence the activa…
Active inference selects actions to maximize information gain, aiding structure learning.
problem Learning the structure of underlying world models.
method Active inference selects actions based on expected free energy, which includes information gain and value.
result Actions that maximize information gain help disambiguate among alternative models.
Study efficient interactive learning for structured outputs with reliable computation.
problem Interactive learning with noisy labels and structured output spaces.
method Identify and utilize CRISPs (probabilistic models) that guarantee reliable and efficient computation of probabilistic quantities.
result CRISPs enable robust and efficient active and skeptical learning in large structured output spaces.
How are economic activities linked to geographic locations? To answer this question, we use a data-driven approach that builds on the information about location, ownership and economic activities of the world's 3,000 largest firms and their almost one million subsidiaries. From this information we generate a bipartite …
Discriminative learning machines often need a large set of labeled samples for training. Active learning (AL) settings assume that the learner has the freedom to ask an oracle to label its desired samples. Traditional AL algorithms heuristically choose query samples about which the current learner is uncertain. This st…
Study efficient active learning for halfspaces with Tsybakov noise using non-convex optimization.
problem Efficiently learn halfspaces with Tsybakov noise under structured unlabeled data.
method Non-convex optimization approach to find approximate first-order stationary points.
result Designs an algorithm with improved label complexity compared to previous methods.
Active Kriging Monte Carlo simulation method with conformal certification for failure probability estimation
problem Failure probability estimation in structural reliability analysis
method Active learning framework with conformal prediction
result Improved uncertainty quantification and reliability of failure probability estimates
A new activation function k-WTA improves neural network defenses against adversarial attacks.
problem Improving neural network robustness against gradient-based adversarial attacks.
method Proposes k-Winners-Take-All activation function and analyzes its effectiveness.
result k-WTA activation significantly enhances neural network robustness against adversarial attacks.
Discriminative classifiers improve decision-making in SHM systems.
problem Lack of descriptive labels for SHM data.
method Risk-based active learning with discriminative classifiers.
result Discriminative classifiers offer improved robustness and reduced inspection costs.
Survey and framework for efficient active learning in structural reliability.
problem Efficiently solving complex structural reliability problems.
method Generalized modular framework combining surrogate model, reliability estimation algorithm, learning function, and stopping criterion.
result 39 strategies for solving 20 reliability benchmark problems, highlighting the importance of surrogates and algorithms.
New insights into data geometry reveal manifold structure in grid-cell activity.
problem Understanding the roles of different dimensions in data geometry.
method Generalised Hanson-Wright inequality and random function model analysis.
result Persistence diagrams reveal latent homology and manifold structure.
This paper converts NACE classification into embeddings to preserve hierarchical structure.
problem Preserving hierarchical structure in NACE classification while reducing dimensions.
method Custom metrics for hierarchical structure retention; state-of-the-art models and dimensionality reduction.
result The proposed approach effectively preserves hierarchical structures in NACE classification.
This paper proposes an active metric learning method for clustering with pairwise constraints.
problem Clustering with pairwise constraints and improving clustering performance.
method Active metric learning method that queries informative instance pairs and updates the learned metric sequentially.
result The proposed method enhances clustering performance and provides a tighter error bound.
Deep learning models outperform classical methods in forecasting neural activity.
problem Improving forecasting of neural activity using deep learning models.
method Systematic evaluation of eight probabilistic deep learning models against classical statistical models and baseline methods.
result Several deep learning models consistently outperform classical approaches in forecasting neural activity.
DEUs learn nonlinear activation functions from data, reducing network size.
problem Fixed activation functions in neural networks limit performance.
method Differential equation units (DEUs) learn nonlinear activation functions from data.
result DEUs enable neurons to change their activation functions during training.
New neural network uses differential equations for adaptable activation functions.
problem Fixed activation functions limit neural network performance and size.
method Introduces differential equation units (DEUs) that learn nonlinear activation functions.
result DEUs enable more compact networks with comparable performance.
New framework interprets deep neural networks through input structure.
problem Limited understanding of how input structure, network parameters, and optimization algorithms work together.
method Introducing a novel theoretical framework based on the compositional structure of piecewise linear activation functions.
result Shows that input instances can be grouped based on their similarity in the internal representation of the neural network.
Study finds Bitcoin crypto currency rate correlates with social network activity.
problem Detecting correlation between crypto currency rate and social network activity.
method Comparative correlation and fractal analysis of time series data.
result Time series of Bitcoin rate and social network activities exhibit self-similar and multifractal properties.
Screening rules help identify active sets in optimization problems.
problem Identifying active sets in optimization problems.
method Screening rules based on subdifferential sets and optimality conditions.
result The number of iterations needed depends only on the convergence rate.
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 consider the problems of detection and localization of a contiguous block of weak activation in a large matrix, from a small number of noisy, possibly adaptive, compressive (linear) measurements. This is closely related to the problem of compressed sensing, where the task is to estimate a sparse vector using a small…
Polynomial neural networks explore thresholds for maximum expressiveness.
problem Understanding the limits of polynomial neural networks' expressiveness.
method Introducing activation degree threshold to measure network expressiveness and proving its existence and upper bounds.
result Polynomial neural networks with equi-width architectures achieve the maximum expressiveness.