Unified RNN handles five feature types for better time series modeling.
problem Handling diverse feature types in time series data.
method Unified RNN framework that separates features into sparse and dense, and incorporates time and static features.
result Unified RNN framework increases performance compared to standard cells.
This research unifies concepts of fading memory in RNNs.
problem Unclear relationships between fading memory concepts in RNNs.
method Unified language and new proofs for fading memory concepts.
result Clarified relationships between fading memory concepts.
RNNs classify text by accumulating evidence on a low-dimensional manifold.
problem Understanding how RNNs solve text classification tasks.
method Dynamical systems analysis applied to trained RNNs.
result RNNs use a low-dimensional attractor manifold to classify text.
Introduces σ-Cell for improved financial volatility forecasting.
problem Improving volatility forecasting in financial markets.
method Combines GARCH and deep learning, incorporating stochastic layers and time-varying parameters.
result Demonstrates superior forecasting accuracy compared to traditional models.
We present a novel view that unifies two frameworks that aim to solve sequential prediction problems: learning to search (L2S) and recurrent neural networks (RNN). We point out equivalences between elements of the two frameworks. By complementing what is missing from one framework comparing to the other, we introduce a…
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.
Unified framework for efficient online training of RNNs.
problem Efficient and biologically plausible online training of recurrent neural networks.
method Organizes algorithms based on criteria like past vs. future facing, tensor structure, stochastic vs. deterministic, and closed form vs. numerical.
result Algorithms cluster according to criteria, revealing conceptual connections.
Unified RNN architecture improves multi-time-horizon solar forecasting.
problem Large prediction errors in traditional solar forecasting methods.
method Recurrent Neural Network (RNN) for multi-time-horizon solar forecasting.
result Lower root-mean-squared prediction error compared to previous methods.
Unified model predicts equipment failure and remaining useful life.
problem Predicting equipment failure and remaining useful life separately is sub-optimal.
method Two methods: Deep Weibull model (DW-RNN) and multi-task learning (MTL-RNN).
result Our methods consistently outperform baseline RUL methods and produce consistent results for RUL and FP.
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.
This paper compares HMC and RNN expressivity using SRT.
problem Comparing expressivity of HMC and RNN models.
method Embed HMC and RNN in a GUM, use SRT to compare structured covariance series.
result Conditions for realizing covariance series by GUM, HMC, or RNN.
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
problem Accurate inflation forecasting is challenging due to dynamic factors and the layered structure of the Consumer Price Index.
method Bi-directional Hierarchical Recurrent Neural Network (BiHRNN) model that uses bidirectional information flow between levels and informative constraints on RNN parameters.
result BiHRNN significantly outperforms traditional RNN models in forecasting accuracy.
The concepts of unitary evolution matrices and associative memory have boosted the field of Recurrent Neural Networks (RNN) to state-of-the-art performance in a variety of sequential tasks. However, RNN still have a limited capacity to manipulate long-term memory. To bypass this weakness the most successful application…
Paper establishes generalization bounds for RNNs and improves existing results.
problem Theoretical understanding and generalization bounds for RNNs.
method New generalization error bound and Rademacher complexity calculation.
result Improved generalization bounds for RNNs, tighter than existing bounds.
Study on memory effects in RNNs learning temporal data.
problem Understanding memory effects in RNNs for temporal data learning.
method Mathematical analysis of continuous-time linear RNNs, focusing on approximation and optimization dynamics.
result Long-term memory requires a large number of neurons and slows down training.
Unified framework for accelerating DNNs on resource-limited platforms.
problem Accelerating DNN execution on resource-limited platforms.
method Block-based pruning framework with reweighted regularization.
result First universal framework for both CNNs and RNNs with real-time acceleration and no accuracy compromise.
Delayed-RNN approximates stacked and bidirectional RNNs.
problem Improving RNN expressiveness and representational capacity.
method Weight-constrained delayed-RNN, equivalent to stacked-RNNs, with partial acausality.
result Delayed-RNN can approximate stacked and bidirectional RNNs, outperforming them in some tasks.
Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs from solving many important computer vision tasks, such as Action Recognition in …
PF-RNNs use particle filtering to model uncertainty in RNNs for better sequential data prediction.
problem Highly variable and noisy sequential data.
method PF-RNNs maintain a latent state distribution as a set of particles, updating with Bayes rule.
result PF-RNNs outperform standard RNNs on various sequence prediction tasks.
In this paper, we explore different ways to extend a recurrent neural network (RNN) to a \textit{deep} RNN. We start by arguing that the concept of depth in an RNN is not as clear as it is in feedforward neural networks. By carefully analyzing and understanding the architecture of an RNN, however, we find three points …
This paper studies a theoretical pruning method for RNNs to reduce computational costs.
problem High computational costs in recurrent neural networks (RNNs).
method Spectral pruning inspired approach for RNNs.
result Generalization error bounds for compressed RNNs are provided.
Lyapunov analysis improves RNN performance prediction.
problem Uncertainty in RNN performance prediction due to hyperparameters and architecture.
method Lyapunov spectral analysis of RNNs and Autoencoder-Lyapunov Embedding Learning (AeLLE).
result AeLLE successfully correlates RNN Lyapunov spectrum with accuracy and predicts performance.
In this work, we propose a novel recurrent neural network (RNN) architecture. The proposed RNN, gated-feedback RNN (GF-RNN), extends the existing approach of stacking multiple recurrent layers by allowing and controlling signals flowing from upper recurrent layers to lower layers using a global gating unit for each pai…
Proposes Fusion Recurrent Neural Network for sequence data.
problem Improving sequence learning for practical applications.
method Fusion module and Transport module for sequence data.
result Fusion RNN performs comparably to state-of-the-art RNNs.
Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we propose an interpretable RNN based on the sequential iterative soft-thresholding al…
Efficient RNN algorithm guarantees convergence in online learning.
problem Online nonlinear regression with RNNs.
method First-order training algorithm with convergence guarantee.
result The algorithm converges to optimum network parameters.
While Recurrent Neural Networks (RNNs) are famously known to be Turing complete, this relies on infinite precision in the states and unbounded computation time. We consider the case of RNNs with finite precision whose computation time is linear in the input length. Under these limitations, we show that different RNN va…
Paper compresses RNNs for resource-constrained devices.
problem Difficulty deploying RNNs on resource-constrained devices.
method Uses Kronecker product (KP) to compress RNN layers.
result KP compresses RNN layers by 16-38x with minimal accuracy loss.
RNNs struggle with in-context retrieval, while Transformers excel.
problem In-context retrieval capability of RNNs.
method Theoretical analysis and experimental techniques (CoT, RAG, Transformer layer).
result Enhancing RNNs with techniques improves their in-context retrieval capability, closing the representation gap with Transformers.
GPU-optimized ES-RNN boosts time series forecasting speed by 322x.
problem Efficiently forecasting time series data.
method Vectorized GPU implementation of ES-RNN.
result Up to 322x speedup in training time.
Paper refines RNN training by analyzing smoothness and attractors.
problem Exploding and vanishing gradients in RNNs.
method Refined concept of exploding gradients using cost function smoothness.
result RNNs need to learn attractors to fully use their power.
TempoPFN models for zero-shot time series forecasting using synthetic data.
problem Efficient long-horizon prediction and reproducibility in zero-shot time series forecasting.
method Linear RNNs pre-trained on synthetic data with GatedDeltaProduct architecture and state-weaving.
result Achieves top-tier competitive performance on various benchmarks.
Novel method improves training RNNs by accelerating gradient descent.
problem Vanishing and exploding gradient problems in RNNs training.
method Adaptive stochastic Nesterov accelerated quasi-Newton method.
result Improved performance in training RNNs with low per-iteration cost.
GIRNet tackles multi-tasking with mixed domain sequences, improving sentiment and tagging tasks.
problem Labeling sequences with mixed domain data and position-specific inference.
method Unified position-sensitive multi-task RNN architecture with gated state sequences from auxiliary data.
result GIRNet achieves new state-of-the-art performance in sentiment classification, POS tagging, and target position-sensitive annotation.
Analyzes RNNs using ODEs to map their properties and improve stability.
problem Understanding and improving the stability of RNNs.
method Relates RNNs to ODEs, mapping their properties to integration methods.
result Establishes sufficient conditions for RNN training stability and designs new architectures.
AC-RNN improves RNN for sequence labeling tasks.
problem RNN's exposure bias in maximum-likelihood training.
method Actor-Critic training for RNNs.
result AC-RNN outperforms CRF on NER and CCG tagging.
Elman-type RNNs converge to globally optimal solutions in the mean-field regime.
problem Optimizing feature learning in wide RNNs.
method Analysis of gradient descent dynamics and mean-field limits.
result Fixed points of infinite-width dynamics are globally optimal.
Deep neural networks have shown promising results for various clinical prediction tasks such as diagnosis, mortality prediction, predicting duration of stay in hospital, etc. However, training deep networks -- such as those based on Recurrent Neural Networks (RNNs) -- requires large labeled data, high computational res…
Recurrent Neural Networks (RNNs) have long been recognized for their potential to model complex time series. However, it remains to be determined what optimization techniques and recurrent architectures can be used to best realize this potential. The experiments presented take a deep look into Hessian free optimization…
New kernels boost RNN performance on non-time-series data.
problem Improving performance of RNNs on non-time-series data.
method Extended RNN kernels to complex architectures, developed fast GPU implementation.
result RNN-based classifiers outperform baselines on 90 non-time-series datasets.
Lyapunov exponents help understand RNN stability.
problem Optimizing RNNs is sensitive to various parameters.
method Use Lyapunov exponents as dynamical system tools.
result Lyapunov spectrum measures training stability.
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.
Study proves deep narrow RNNs can approximate any function, with minimum width independent of data length.
problem Proving universality of deep narrow RNNs with bounded widths.
method Analyzing RNNs as dynamical systems, proving universality for deep narrow structures with specific widths.
result Minimum width for universality of deep narrow RNNs is independent of data length.
Hamiltonian RNN controls hidden states gradient for long-term dependencies.
problem Challenges in learning long-term dependencies in RNNs.
method Symplectic discretization of Hamiltonian system to control gradient.
result Hamiltonian RNN outperforms other RNNs without hyperparameter optimization.
We introduce MinimalRNN, a new recurrent neural network architecture that achieves comparable performance as the popular gated RNNs with a simplified structure. It employs minimal updates within RNN, which not only leads to efficient learning and testing but more importantly better interpretability and trainability. We…
Frequentist method estimates uncertainty in RNNs without altering architecture.
problem Uncertainty quantification in RNNs for decision-making.
method Jackknife resampling and influence functions to estimate variability.
result The method provides theoretical coverage guarantees on uncertainty intervals.
This paper proposes structurally sparse RNNs to reduce computational and memory costs.
problem Heavy computational and memory burden in fully connected RNNs.
method Study structurally sparse RNNs, reducing recurrent operations and weights.
result Structurally sparse RNNs achieve competitive performance with reduced costs.
A new model combines spatial and spectral features for HSI classification.
problem Inefficiency and difficulty in training RNNs for HSI classification.
method Proposes St-SS-pGRU combining shorten RNN, converlusion layer, and parallel-GRU.
result Better performance and robustness in HSI classification.