Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions. In the present work, we extend the usage of LRP to recurrent neural networks. We propose a specif…
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.
169,181 papers · 148 categories
Trend · papers per month
48 results for “LRP technique”
Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing (NLP). More precisely, we use it to explain the predictions of a convolutional n…
Deep networks analyze video snippets to predict outcomes, revealing a border effect that can be adjusted for better accuracy.
problem Improving the accuracy of deep networks trained on small video snippets.
method Applied the deep Taylor / LRP technique to understand and identify a border effect, tuning the step size to improve accuracy.
result The step size used to build video snippets can be adjusted to improve deep network accuracy without retraining.
Proposes a deep learning model to improve stock market prediction.
problem Lack of interpretability in linear multi-factor models for stock prediction.
method Extends linear multi-factor model to LSTM+LRP for non-linear and time-varying predictions.
result Deep recurrent factor model outperforms traditional models in predictive capability.
New research validates a best practice for explaining neural network decisions.
problem Transparency in neural network decision-making.
method Layer-wise Relevance Propagation (LRP) with layer-dependent approach.
result Layer-dependent LRP better represents model reasoning and improves object detection.
Background: In cognitive neuroscience the potential of Deep Neural Networks (DNNs) for solving complex classification tasks is yet to be fully exploited. The most limiting factor is that DNNs as notorious 'black boxes' do not provide insight into neurophysiological phenomena underlying a decision. Layer-wise Relevance …
Adapts LRP for LSTM to explain sequential data.
problem Lack of explainable AI for LSTM models.
method Extends LRP to LSTM, introduces new propagation scheme.
result Delivers faithful explanations for LSTM predictions.
New method explains GNN predictions using walks.
problem GNNs are black-boxes and hard to explain.
method Nested attribution scheme using relevant walks.
result Extracts meaningful explanations from GNNs.
MambaLRP enhances Mamba models' explainability and performance.
problem Lack of transparency in Mamba models for real-world applications.
method Layer-wise Relevance Propagation (LRP) with relevance conservation axioms.
result MambaLRP provides stable and reliable explanations for Mamba models.
DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-layer networks with millions of parameters. This is a cause for concern since linear models are simple …
XAI identifies key time steps for early crop classification.
problem Early crop classification with high accuracy and timeliness.
method Training a baseline model with LRP to identify important time steps.
result Identified a 21st April 2019 to 9th August 2019 timeframe with 0.75% accuracy loss.
Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment. Machine learning (ML) models have been trained to automatically map documents to these abstract concepts, allowing to annotate very large text collections, more than could be processed by a human in …
iNNvestigate simplifies neural network analysis.
problem Understanding and analyzing complex neural networks is difficult.
method Provides a common interface and implementation for analysis methods.
result Demonstrates versatility in analyzing various neural network architectures.
Deep Factor Modelq-fin.ST
Unified return and risk modeling using deep learning with interpretability.
problem Lack of transparency and interpretability in deep learning models.
method Construct a multifactor model using interpretable deep learning, decompose attributes using LRP.
result Deep factor model outperforms traditional models in predictive capability.
Deep learning explains individual gait patterns in clinical biomechanics.
problem Understanding complex gait patterns from medical data.
method Layer-Wise Relevance Propagation (LRP) technique to attribute relevance of input variables to model predictions.
result Demonstrates which input variables are most relevant for characterizing individual gait patterns.
New method explains predictive uncertainty by focusing on second-order effects.
problem Explaining predictive uncertainty in machine learning models.
method CovLRP, CovGI, etc., based on second-order effects.
result Predictive uncertainty is dominated by second-order effects.
Study investigates XAI methods in clinical gait analysis.
problem Limited understanding of machine learning models in healthcare.
method XAI methods, specifically Layer-wise Relevance Propagation (LRP), to explain ML predictions.
result Explanations from LRP show promising statistical and clinical relevance.
Paper explains distance-based classifiers using neural network structures.
problem Making distance-based classifiers explainable.
method Uncovering latent neural network structures in distance-based classifiers.
result Novel explanation approach outperforms baselines.
Paper shows convergence rates for stochastic processes.
problem Analyzing convergence rates for stochastic processes.
method Quantitative convergence in for Langevin-like processes.
result Iterates converge to an invariant distribution at rate .
The paper introduces logic constraints to improve AI model interpretability.
problem The black box nature of AI models limits their trustworthiness in high-stakes fields.
method The paper extends AI models with logic constraints to make feature importance more interpretable.
result Promising experimental results have been achieved for the Adult dataset.
Physically Interpretable Neural Networks for the Geosciences: Applications to Earth System Variabilityphysics.ao-ph
Neural networks improve geoscience by enabling interpretable decision pathways.
problem Lack of methods to interpret neural networks' learning and decision-making.
method Backwards optimization and layerwise relevance propagation.
result Interpretation techniques reveal meaningful connections in geoscientific data.
DeepLight uses LSTM to decode fMRI data, improving cognitive state analysis.
problem Challenges in analyzing neuroimaging data due to high dimensionality, low sample size, and complex dependency structure.
method Introduces DeepLight framework using LSTM-based DL models to process fMRI data sequences, adapts LRP for interpretability.
result DeepLight outperforms conventional fMRI analysis methods in decoding cognitive states and identifying brain regions.
Modified BP attribution methods often ignore later layers' information, leading to misleading explanations.
problem Misleading explanations from modified BP methods ignoring later layers' information.
method Analysis of 9 modified BP methods including Deep Taylor Decomposition, LRP, Excitation BP, PatternAttribution, DeepLIFT, Deconv, RectGrad, Guided BP.
result Only DeepLIFT does not ignore later layers' information, providing a faithful explanation.
Interprets how intrinsic motivation shapes behavior in RL agents.
problem Understanding how intrinsic motivation influences behavior in reinforcement learning agents.
method Analyzed five RL agents in procedurally generated environments using various interpretability techniques.
result Curiosity-driven agents exhibit broader and more dynamic attention than extrinsically motivated agents.
Study compares neural networks for age and gender recognition, revealing feature importance and robustness.
problem Understanding which facial features are used and how preprocessing affects deep neural networks for age and gender recognition.
method Compared four neural network architectures, evaluated preprocessing robustness, visualized prediction strategies.
result Suitable parameter initialization improves holistic perception of input, leading to state-of-the-art performance in gender recognition.
Adversarial manipulation fools neural network interpretations.
problem Ensuring interpretation methods are robust to model manipulations.
method Integrating manipulation into fine-tuning objective function.
result State-of-the-art interpreters can be fooled with minimal accuracy loss.
nFBST tests neural networks using Bayesian methods.
problem Traditional significance testing struggles with complex nonlinear relationships.
method nFBST uses Bayesian neural networks to test neural networks.
result nFBST can test global, local, and instance-wise significance.
BiLRP explains deep similarity models by decomposing scores into feature contributions.
problem Verifying meaningful patterns in complex similarity models.
method Augmenting similarity scores with feature explanations using LRP.
result BiLRP robustly explains deep neural network features and historical document similarities.
Proposes a new feature-based evaluation method for explaining Deep Learning models in text classification.
problem Lack of consideration for linguistic dependencies in existing attribution-based explanations.
method Investigates perturbations based on embedded features removal from intermediate layers of Convolutional Neural Networks.
result Visualization tool assists analysts in understanding model predictions better.
XAI methods struggle with identifying true predictors from suppressors in linear datasets.
problem XAI methods misidentify suppressor variables as important features.
method Carefully crafted linear ground-truth dataset to study suppressor variables; evaluated various XAI methods.
result Most XAI methods fail to distinguish true predictors from suppressors in linear settings.
We present a large-scale study of commonality in liquidity and resilience across assets in an ultra high-frequency (millisecond-timestamped) Limit Order Book (LOB) dataset from a pan-European electronic equity trading facility. We first show that extant work in quantifying liquidity commonality through the degree of ex…
Pixel-wise relevance method shows how CNNs classify faces, varying across datasets and tasks.
problem Interpreting black-box CNN face recognition models.
method Layer-wise relevance propagation (LRP) applied to VGG-16 models trained for face recognition.
result Relevance maps are generally stable across random initializations and tasks, but less so across pretraining datasets.
Study finds different active learning techniques better for various learning objectives.
problem Matching active learning techniques to specific learning objectives.
method Survey of students' perceptions and ratings of various techniques.
result Different active learning techniques are best suited for different learning objectives.
Analyzing different prototype selection techniques for dynamic classifier and ensemble selectioncs.LG
Prototype selection improves DS techniques' accuracy and reduces computational cost.
problem Improving the performance of dynamic selection techniques.
method Prototype selection techniques that edit validation data to remove noise and redundant instances.
result Improves DS techniques' classification accuracy and reduces computational cost.
Enhanced Bayesian target encoding uses sampling techniques to improve model performance.
problem Improving target encoding for better model performance in machine learning.
method Using sampling techniques in Bayesian target encoding to extract intra-category distribution information.
result Improves generalization and reduces target leakage in machine learning models.
Adapts pivoting technique to circle homeomorphisms for proofs.
problem Probabilistic Tits alternative and exponential synchronization.
method Adapts Gou{ë}zel's pivoting technique.
result Different proofs of probabilistic Tits alternative and exponential synchronization.
This review covers AI in finance, challenges, techniques, and opportunities.
problem Challenges and opportunities in AI applications in finance.
method Comprehensive categorization and overview of AI research in finance over decades.
result A dense roadmap of AI challenges, techniques, and opportunities in finance.
Survey of extreme value modeling techniques for insurance.
problem Modeling of insurance industry's extreme events.
method Truncation, tempering, censoring, regression techniques.
result Adapted techniques for insurance applications.
Framework converts singer identity and vocal technique from non-parallel corpora.
problem Converts singer identity and vocal technique from non-parallel corpora.
method Uses variational autoencoders with separate encoders for singer identity and vocal technique.
result Successfully disentangles and converts singer identity and vocal technique.
This article is written for the Proceedings of the Conference on Current Developments in Mathematics in Harvard University, November 16-17, 2007. It is an exposition of the analytic proof of the finite generation of the canonical ring for a compact complex algebraic manifold of general type. It lists and discusses the …
New displacement technique vanishes bounded cohomology in all degrees.
problem Vanishing of bounded cohomology in all positive degrees and dual separable coefficients.
method Introducing the property of commuting cyclic conjugates as a new displacement technique.
result Vanishes bounded cohomology in all positive degrees and all dual separable coefficients.
Models obtained by decision tree induction techniques excel in being interpretable.However, they can be prone to overfitting, which results in a low predictive performance. Ensemble techniques are able to achieve a higher accuracy. However, this comes at a cost of losing interpretability of the resulting model. This ma…
Study harmonic mappings and submanifolds using Bochner technique.
problem Classical theorems in harmonic mappings and submanifolds.
method Generalized Bochner technique.
result New insights into classical theorems.
Overview of SML techniques with banking applications.
problem Credit risk modeling in banking.
method Tree-based ensemble algorithms, Feedforward NNs, hyper-parameter optimization, machine learning interpretability.
result Comparison of ML algorithm features and their application in banking.
Reduces survival analysis to common regression tasks.
problem Applying standard machine learning tools to survival analysis.
method Various reduction techniques to simplify survival analysis.
result Benchmark analysis shows improved predictive performance.
This study reviews techniques to estimate volatility and price Variance Swaps.
problem Estimating historical volatility and pricing Variance Swaps.
method Review of existing techniques.
result Discussion of various methods to estimate volatility and price Variance Swaps.
This review explores resampling techniques for imbalanced binary classification.
problem Imbalanced classes lead to poor prediction results in classification.
method Classical, cost-sensitive, and Neyman-Pearson paradigms with resampling techniques and classification methods.
result Complex dynamics among resampling techniques, base methods, metrics, and imbalance ratios.
New methods show hyperbolicity of Brunnian links.
problem Determining hyperbolicity of Brunnian links.
method Geometric/combinatorial topology techniques applied to links with at least one unknotted component.
result Determine hyperbolicity for all Brunnian links.