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.

168,742 papers · 148 categories

Trend · papers per month

count % of corpus

19 results for “CNN-RNN”

A CNN-RNN Framework for Crop Yield Predictioncs.LG

Deep learning model predicts crop yields using CNN-RNN.

problem Challenges in predicting crop yields due to multiple factors.

method CNN-RNN framework using environmental and management data.

result CNN-RNN model outperformed other methods by 9-8% RMSE.

crop yield prediction deep learning CNN-RNN environmental data management practices

2019-11-20abs ↗pdf ↗

A Multi-component CNN-RNN Approach for Dimensional Emotion Recognition in-the-wildcs.CV

This paper presents our approach to the One-Minute Gradual-Emotion Recognition (OMG-Emotion) Challenge, focusing on dimensional emotion recognition through visual analysis of the provided emotion videos. The approach is based on a Convolutional and Recurrent (CNN-RNN) deep neural architecture we have developed for the …

2018-05-03abs ↗pdf ↗

Explanatory Masks for Neural Network Interpretabilitycs.LG

Develops masks to explain neural network predictions.

problem Improving neural network interpretability for various applications.

method Creates explanation masks for pre-trained networks using a secondary network.

result Demonstrates the effectiveness of the method across different types of networks.

interpretability neural networks masks prediction CNNs

2019-11-15abs ↗pdf ↗

Comparison of Neural Network Architectures for Spectrum Sensingeess.SP

Different neural network (NN) architectures have different advantages. Convolutional neural networks (CNNs) achieved enormous success in computer vision, while recurrent neural networks (RNNs) gained popularity in speech recognition. It is not known which type of NN architecture is the best fit for classification of co…

2019-07-15abs ↗pdf ↗

Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuningeess.AS

Deep CNN-RNN model classifies breathing sounds for respiratory disease diagnosis.

problem Automated diagnosis of respiratory diseases using wearable devices.

method Patient-specific model tuning and local log quantization of weights.

result 71.81% accuracy on leave-one-out validation with patient-specific data.

Respiratory Sound Classification Wearable Devices Deep Learning Patient Specific Models Wheeze

2020-04-16abs ↗pdf ↗

Exploiting multi-CNN features in CNN-RNN based Dimensional Emotion Recognition on the OMG in-the-wild Datasetcs.LG

This paper presents a novel CNN-RNN based approach, which exploits multiple CNN features for dimensional emotion recognition in-the-wild, utilizing the One-Minute Gradual-Emotion (OMG-Emotion) dataset. Our approach includes first pre-training with the relevant and large in size, Aff-Wild and Aff-Wild2 emotion databases…

2019-10-03abs ↗pdf ↗

RPN 2: On Interdependence Function Learning Towards Unifying and Advancing CNN, RNN, GNN, and Transformercs.LG

RPN 2 improves function learning by modeling data interdependence.

problem Invalid assumption of input data independence leads to performance degradation.

method Integrates data and structural interdependence functions into RPN 2's architecture.

result Significantly improves learning performance and expands unifying potential.

data interdependence function learning RPN 2 CNN RNN

2024-11-17abs ↗pdf ↗

Temporally Folded Convolutional Neural Networks for Sequence Forecastingcs.LG

A new CNN approach for time series forecasting outperforms traditional RNNs.

problem Time series forecasting using conventional RNNs.

method Temporally folded convolutional neural networks (TFC's) for sequence forecasting.

result TFC's outperform conventional RNNs on sequential MNIST and JSB chorals datasets.

CNN RNN Sequence Forecasting Temporal Folding Convolutional LSTM

2020-01-10abs ↗pdf ↗

Interpretable Deep Neural Networks for Dimensional and Categorical Emotion Recognition in-the-wildcs.LG

Project extends emotion recognition database and trains neural networks for categorical and dimensional emotions.

problem Understanding and recognizing emotions for human-computer interaction, safety, and medical research.

method Training CNN + RNN models with emotion category and valence/arousal representations, comparing three model types.

result Categorical emotion recognition performance improves with combined model training.

emotion recognition deep learning neural networks categorical dimensional

2019-10-13abs ↗pdf ↗

FineHand: Learning Hand Shapes for American Sign Language Recognitioncs.CV

FineHand learns hand shapes for better ASL recognition.

problem Difficult ASL recognition due to fast, articulate gestures.

method Combines manual and deep learning for hand shape embeddings, uses RNN for sequential gestures.

result Improved video gesture recognition accuracy on GMU-ASL51 benchmark.

ASL recognition hand shape deep learning CNN RNN

2020-03-04abs ↗pdf ↗

Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transformcs.LG

Efficiently optimizes CNN and RNN parameters on Stiefel manifold.

problem Computational expense in optimizing orthonormal matrices on Stiefel manifold.

method Cayley transform for efficient retraction and vector transport on Stiefel manifold.

result Cayley SGD and ADAM achieve faster convergence and less training time.

Riemannian optimization Stiefel manifold Cayley transform CNN RNN

2020-02-04abs ↗pdf ↗

A large-scale evaluation framework for EEG deep learning architectureseess.SP

EEG is the most common signal source for noninvasive BCI applications. For such applications, the EEG signal needs to be decoded and translated into appropriate actions. A recently emerging EEG decoding approach is deep learning with Convolutional or Recurrent Neural Networks (CNNs, RNNs) with many different architectu…

2018-06-18abs ↗pdf ↗

Classification of sparsely labeled spatio-temporal data through semi-supervised adversarial learningstat.ML

In recent years, Generative Adversarial Networks (GAN) have emerged as a powerful method for learning the mapping from noisy latent spaces to realistic data samples in high-dimensional space. So far, the development and application of GANs have been predominantly focused on spatial data such as images. In this project,…

2018-01-26abs ↗pdf ↗

Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classificationcs.IR

CNNs, RNNs, GCNs, and CapsNets have shown significant insights in representation learning and are widely used in various text mining tasks such as large-scale multi-label text classification. However, most existing deep models for multi-label text classification consider either the non-consecutive and long-distance sem…

2019-06-09abs ↗pdf ↗

Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescs.LG

Unified geometric principles unify neural network architectures.

problem High-dimensional learning tasks with underlying low-dimensionality and structure.

method Unified geometric principles applied to neural network architectures.

result Unified mathematical framework for neural network architectures.

Geometric Deep Learning Neural Networks Feature Learning Unified Framework Erlangen Program

2021-04-27abs ↗pdf ↗

CRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal Detectioncs.LG

Earthquake signal detection is at the core of observational seismology. A good detection algorithm should be sensitive to small and weak events with a variety of waveform shapes, robust to background noise and non-earthquake signals, and efficient for processing large data volumes. Here, we introduce the Cnn-Rnn Earthq…

2018-10-03abs ↗pdf ↗

Temporal Collaborative Ranking Via Personalized Transformercs.LG

The collaborative ranking problem has been an important open research question as most recommendation problems can be naturally formulated as ranking problems. While much of collaborative ranking methodology assumes static ranking data, the importance of temporal information to improving ranking performance is increasi…

2019-08-15abs ↗pdf ↗

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networkscs.LG

LC-PFN predicts learning curve performance more accurately and faster than MCMC.

problem Bayesian extrapolation of learning curves is computationally expensive and overly restrictive.

method Prior-Data Fitted Neural Networks (PFNs) for approximate Bayesian inference.

result LC-PFN outperforms MCMC in accuracy and is significantly faster.

learning curve extrapolation Bayesian inference PFNs neural networks model selection

2023-10-31abs ↗pdf ↗

Mean field theory for deep dropout networks: digging up gradient backpropagation deeplycs.LG

Mean field theory explains gradient backpropagation in deep dropout networks.

problem Understanding gradient backpropagation in deep dropout networks.

method Applied mean field theory to dropout networks, considering realistic training conditions.

result Gradient backpropagation length is limited by depth scales, not just independence assumption.

mean field theory dropout networks gradient backpropagation neural networks universal phenomena

2019-12-19abs ↗pdf ↗