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.
Paper tackles OMG-Emotion Challenge with CNN-RNN for dimensional emotion recognition.
problem Dimensional emotion recognition in-the-wild from visual analysis.
method Developed a multi-component CNN-RNN deep neural architecture for AffWild Emotion Database.
result Best architectures for valence and arousal estimation over validation data.
Paper presents a CNN-RNN method for multi-dimensional emotion recognition in-the-wild.
problem Dimensional emotion recognition in real-world scenarios.
method Pre-training with Aff-Wild and Aff-Wild2, extracting low-, mid-, and high-level features, using RNN subnets in a multi-task framework, and fusion of networks.
result Our approach outperformed state-of-the-art methods using only visual information.
CNN-RNNs detect bird sounds with high accuracy.
problem Automated detection of bird sounds in varied environments.
method Convolutional Recurrent Neural Networks (CNN-RNNs) for feature extraction and dependency capture.
result 88.5% AUC score on unseen data.
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.
This work compares NN architectures for spectrum sensing.
problem Choosing the best neural network architecture for spectrum sensing.
method Comparison of fully-connected NN (FC), CNN, RNN, and BiRNN.
result CNN, RNN, and BiRNN achieve similar performance.
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.
Unified detection of isolated and overlapping audio events using CNN-RNN.
problem Detecting both isolated and overlapping audio events simultaneously.
method Multi-label multi-task framework based on CNN-RNN, with sequential losses.
result Good generalization on isolated and overlapping audio event detection datasets.
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.
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.
Paper uses DL and image embedding to classify power grid disturbances.
problem Classifying transient disturbances in power grids.
method Transformed time series data into images using Gramian Angular Field, then applied CNN and RNN for classification.
result DL algorithms outperform traditional data mining methods in power grid disturbance classification.
Combines CNN and RNN for hierarchical image classification.
problem Hierarchical relations between image categories are not captured by flat classifiers.
method Uses a CNN for feature extraction and an RNN for capturing hierarchical class relations. Incorporates residual learning.
result Hierarchical networks outperform state-of-the-art CNNs on a real-world dataset.
GCRN models graph-structured sequences with CNN and RNN.
problem Predicting structured sequences of data.
method Combines CNN and RNN on graphs.
result Improves precision and learning speed.
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.
Study shows fewer samples needed for CNNs and RNNs than FNNs.
problem Estimating the number of samples needed for CNNs and RNNs.
method Localized empirical process analysis and new lemma characterizing CNNs and RNNs.
result Sample complexity scales linearly with intrinsic dimension for CNNs and RNNs.
Method trains deep neural networks on weakly labeled audio data efficiently.
problem Limited training data and lack of temporal labels for audio event detection.
method Multi-instance learning with a new loss function for stacked CNN-RNN.
result Improved performance on low-resource audio datasets.
PTU learns fine-grained parameter transfer for deep networks.
problem Discrete transfer states and lack of principled approach to learn transfer strategies.
method PTU learns a fine-grained nonlinear combination of activations from source and target networks using two gates.
result PTU outperforms heuristic methods in most settings.
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.
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.
Framework evaluates deep learning EEG architectures on 100 datasets.
problem Evaluating different deep learning architectures for EEG signal decoding.
method Large-scale evaluation framework with 100 EEG datasets and multiple decoders.
result Comparison of three CNN architectures on different EEG tasks.
Method learns latent representations from spatio-temporal data.
problem Modeling dynamic data over time.
method Semi-supervised adversarial learning with GANs and RNNs.
result Competitive classification performance of latent representations.
New method compares neural network representations, revealing generalization and structure.
problem Comparing neural network representations is hard due to varying structures and evolution.
method Projection Weighted CCA (CCA) to differentiate signal and noise.
result Networks that generalize converge to similar representations, while memorizers diverge.
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.
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.
Proposes a novel framework for multi-label text classification.
problem Lack of coherent consideration of non-consecutive and long-distance semantics and hierarchical relations among labels.
method Hierarchical taxonomy-aware and attentional graph capsule recurrent CNNs framework.
result Significantly improves multi-label text classification performance.
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.
CRED detects microearthquakes efficiently and reliably.
problem Detecting small and weak earthquake signals in noisy data.
method Deep neural network combining convolutional and recurrent units.
result 99.95 F-score on validation data, detects microearthquakes far from training region.
Personalized Transformer improves temporal collaborative ranking performance.
problem Temporal collaborative ranking in recommendation systems.
method Personalized Transformer model using attention mechanisms.
result Personalized Transformer outperforms SASRec by almost 5% in NDCG@10.
Deep learning models improve spatio-temporal data mining.
problem Mining valuable knowledge from spatio-temporal data.
method Application of deep learning techniques (CNN, RNN) in various spatio-temporal data mining tasks.
result Deep learning models enhance performance in spatio-temporal data mining.
MetaPred uses meta-learning to improve clinical risk prediction from limited EHR data.
problem Clinical risk prediction from sparse patient EHR data.
method Meta-learning approach to train a meta-learner from related tasks, then fine-tune for target risk prediction.
result MetaPred achieves better performance for target risk prediction with limited data.