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.

169,181 papers · 148 categories

Trend · papers per month

2535067591,012 · Jun 202019922001200920182026
48 results for living neural networks

Deep learning model classifies human activities without prior knowledge.

problem Human activity recognition using smart home sensors.
method Long Short Term Memory (LSTM) Recurrent Neural Network applied to three real-world datasets.
result The proposed approach outperforms existing methods in terms of accuracy and performance.

Deep learning and genetic algorithms speed up cosmological Bayesian inference.

problem Substantial computational demands in Bayesian inference for cosmological parameter estimation.
method Deep learning using feedforward neural networks to approximate likelihood functions dynamically, optimized with genetic algorithms.
result Significant speed-up in Bayesian inference process for cosmological models and datasets.

Deep neural network assesses quality of super-resolution images.

problem Evaluating the quality of super-resolution images from experts' scores.
method Deep neural network trained on expert scores to quantify image quality.
result Deep neural network's quality predictions correlate with human expert evaluations.

Improved neural network predicts tropical storm trajectories and Bayesian intervals.

problem Accurately predicting the trajectories of tropical storms to prevent damage.
method Developed an improved RNN model with dropout to predict Bayesian intervals.
result Neural network dropout values significantly affect prediction accuracy and intervals.

System recommends workouts and predicts success rates using RNNs.

problem Promoting healthy lifestyles through personalized exercise recommendations.
method Two interconnected recurrent neural networks (RNNs) using historical workout data.
result Interconnected-RNN model predicts exercise success rates with improved accuracy.

AI-assisted heart disease diagnosis reduces misdiagnosis and saves lives.

problem Misdiagnosis of heart disease leads to unnecessary deaths.
method Developed an AI application using ML and DNN algorithms on a dataset from the Cleveland Clinic Foundation.
result DNN model achieved a 92% accuracy rate, reducing misdiagnosis.

Improved action recognition in live videos with hybrid FR-DL method.

problem High computational costs and lack of temporal information in conventional action recognition.
method Automated selection of representative frames, feature extraction, background subtraction, HOG, deep neural network, LSTM, Softmax-KNN classifier.
result Significant improvement in accuracy and speed compared to state-of-the-art methods.

Persistent homology reveals a topological signature of grokking in neural networks.

problem Understanding how neural networks learn and generalize from modular arithmetic tasks.
method Persistent homology on point clouds derived from embedding matrices of models trained on modular arithmetic.
result A sharp increase in first homology persistence indicates grokking, with a dominant long-lived topological feature and structured secondary features.

Statistical model for analyzing longitudinal data on Riemannian manifolds.

problem Analyzing longitudinal data on non-Euclidean spaces.
method Developed a recurrent statistical model for ordered data on Riemannian manifolds.
result Efficient algorithm with competitive performance and fewer parameters.

New test uses neural networks to compare distributions, outperforming traditional methods.

problem Comparing distributions in high dimensions and higher orders of smoothness.
method Integral probability metrics with Radon bounded variation functions and neural networks.
result The Radon-Kolmogorov-Smirnov (RKS) test outperforms traditional methods in distinguishing distributions.

Deep neural network predicts product returns before purchase.

problem High costs of handling returned fashion products.
method Bayesian Personalized Ranking (BPR) embeddings and skip-gram model for user and product features.
result Reduced overall returns through real-time return probability prediction.

Deep learning shows neural networks can be trained with limited data, revealing a low-dimensional manifold of optimal configurations.

problem How neural networks can be trained with limited data despite having billions of potential configurations.
method Using mutual information between layers of a deep neural network to speed up training and find optimal configurations.
result Adding structure to neural networks that enforces higher mutual information between layers speeds training and leads to more accurate results.

Study improves forecasting in betting markets using novel neural networks.

problem Improving short-term price movement predictions in betting exchanges.
method Innovative convolutional attention mechanisms applied to recurrent neural networks and bi-dimensional layers.
result All proposed innovations positively impact classification task performance.

Study creates a global living index to assess quality of life.

problem Long-term impacts of global economic changes on living conditions.
method Machine learning framework combining socio-economic factors.
result Developed a practical tool for policymakers to identify areas needing improvement.

New method learns intrinsic manifold from observed data for accurate localization.

problem Learning latent intrinsic geometry from observed high-dimensional data.
method Intrinsic Isometric Manifold Learning (IIML) using neural networks for metric estimation.
result IIML achieves accurate localization in ad-hoc sensor networks from imaging data.

This paper reviews hyper-parameter optimization methods for deep learning.

problem Designing and training deep neural networks is challenging and unpredictable.
method Reviews major optimization algorithms and services for hyper-parameter tuning.
result Comprehensive comparison of optimization algorithms and services.

AFP-CKSAAP predicts antifreeze proteins using k-spaced amino acid pairs with deep neural networks.

problem Predicting antifreeze proteins due to their diverse sequence characteristics.
method Deep neural network with skipped connections and ReLU non-linearity to learn protein sequence descriptors.
result AFP-CKSAAP achieves excellent prediction scores and high Youden's index (0.82) on independent dataset.

Smart meters detect dementia patients' daily activities to prevent crises.

problem Monitoring dementia patients' daily activities without intruding.
method Machine learning and signal processing for smart meter load disaggregation.
result SVM and Decision Forest models accurately detect ADLs and routine changes.

Study predicts social relationships using triadic influence from social networks.

problem Difficulty in quantifying social relationships and their dynamics.
method Real social networks of 13 schools, neural networks, high-dimensional embedding.
result Triadic influence achieves highest accuracy in predicting student relationships.

SoftAdapt dynamically adjusts loss weights for multi-part functions.

problem Slow convergence and poor weight selection for multi-part loss functions.
method SoftAdapt dynamically changes weights based on live performance statistics.
result Improved convergence and better weight selection for multi-part loss functions.

This paper analyzes CNNs for malware detection in cloud IaaS.

problem Malware vulnerability in cloud IaaS environments.
method Analysis of Convolutional Neural Networks (CNNs) for online malware detection using process-level performance metrics.
result State-of-the-art DenseNets and ResNets effectively detect malware in online cloud systems.

Backtests of structured strategies lose much of their predictive power in live trading.

problem Uncertainty in how marketed backtests predict live performance of structured strategies.
method Analysis of 1,726 structured strategies from ten global institutions.
result Raw backtests have limited portability into live trading and deteriorate sharply.

Real-time system detects accidents to save lives and reduce congestion.

problem Traffic congestion and accidents causing casualties and wasted time.
method Big data processing and computational intelligence techniques.
result The system can predict the possibility of accidents, even with false alarms.

This paper optimizes resource allocation for crowdsourced live streaming to improve viewer experience and reduce costs.

problem Improving viewer quality of experience (QoE) in crowdsourced live streaming.
method A prediction-driven resource allocation framework using machine learning to predict viewer numbers and proactively allocate resources.
result Maximizes viewer QoE and minimizes resource allocation costs through precise resource provisioning.