RNF learns distinct representations for Bayesian filtering steps, improving time series prediction accuracy and uncertainty.
problem Improving time series prediction accuracy and uncertainty using distinct representations for Bayesian filtering steps.
method Introduces Recurrent Neural Filter (RNF) architecture that learns distinct representations for each Bayesian filtering step.
result RNF improves accuracy of one-step-ahead forecasts and provides realistic uncertainty estimates.
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.
New algorithm speeds up RNN time series prediction by filtering noise.
problem Predicting smooth trajectories from noisy time series data.
method Analyzed RNN dynamics to propose an efficient noise filtering algorithm.
result Significant speedup in predictive process without accuracy loss.
This study uses neural networks to approximate Bayesian filtering problems.
problem Estimating latent time-series signal statistics from observation sequences.
method Formulated a generic recurrent neural network framework to learn recursive mappings directly.
result Approximation error bounds for filtering in non-compact domains and strong time-uniform bounds.
Recursive KalmanNet combines neural networks with Kalman filters for precise state estimation.
problem State estimation in systems with noisy measurements and non-Gaussian noise.
method Recursive KalmanNet uses a recurrent neural network to estimate states with consistent error covariance, optimizing for Gaussian negative log-likelihood.
result Recursive KalmanNet outperforms conventional Kalman filters and deep learning-based estimators in non-Gaussian noise conditions.
GCRNNs improve graph problem solving with fewer parameters.
problem Graph process problems like earthquake epicenter identification and weather prediction.
method GCRNNs use convolutional filter banks and time-gated variations of GCRNNs (Gated GCRNNs) to improve performance.
result GCRNNs significantly improve performance over GNNs and another graph recurrent architecture.
New kernel-based models improve on traditional neural methods in sequence modeling.
problem Sequence modeling challenges in natural language processing and neuroscience.
method Kernel-based recurrent neural networks and convolutional neural networks.
result Kernel-based models perform on par or better than traditional neural methods.
CRUs model irregular time series with continuous hidden states.
problem Handling irregular time intervals in sequential data.
method Continuous Recurrent Units (CRUs) that integrate hidden states via a linear stochastic differential equation.
result CRUs outperform methods based on neural ordinary differential equations in irregular time series interpolation.
Proposes CVRCF for streaming recommender systems combining deep learning and probabilistic models.
problem Streaming recommendation problem with dynamic data and complexity.
method Coupled Variational Recurrent Collaborative Filtering (CVRCF) framework integrating stochastic processes and deep factorization models.
result Favorable performance in temporal dependency modeling and predictive accuracy compared to state-of-the-art methods.
Linear recurrent networks explain reinforcement learning performance in partially observable settings.
problem Understanding why linear recurrent networks work in reinforcement learning with partial observability.
method Constructed and studied two linear filters for HMMs and action-controlled HMMs.
result Linear filters serve as sufficient statistics and reduce state ambiguity, explaining empirical reinforcement learning success.
Develops a tensor network framework to reduce RNN complexity for high-dimensional sequence modeling.
problem Exponential parameter growth in RNNs for large multidimensional data.
method Embeds a multi-linear graph filter in a tensor network architecture to approximate RNN hidden states.
result Demonstrates superior performance and reduced complexity compared to traditional RNNs.
Combines Fourier methods and RNNs for efficient time series prediction.
problem Efficiently processing and predicting time series data with memory and computational constraints.
method Uses short-time Fourier transform and weight reductions through low pass filtering in a Spectral RNN.
result Predicts time series data from chaotic systems and real-world data.
Recent work has shown that collaborative filter-based recommender systems can be improved by incorporating side information, such as natural language reviews, as a way of regularizing the derived product representations. Motivated by the success of this approach, we introduce two different models of reviews and study t…
Mathematical study of learning long-term integration in linear RNNs.
problem How do linear recurrent neural networks learn to integrate over long timescales?
method Analytical study of linear RNNs trained to integrate white noise and damped oscillatory filters.
result Learning dynamics are described by low-dimensional effective equations for outlier eigenvalues.
Paper uses RNNs for more accurate indoor WiFi localization.
problem Accurate indoor WiFi localization using RSSI measurements.
method Proposes recurrent neural networks (RNNs) for trajectory positioning of RSSI data.
result Achieves an average localization error of 0.75 m with 80% under 1 m, outperforming conventional algorithms.
We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems. PSRNNs draw on insights from both Recurrent Neural Networks (RNNs) and Predictive State Representations (PSRs), and inherit advantages from both types of models. Like many successful RNN archi…
Recursive KalmanNet generalizes well in noisy, out-of-distribution scenarios.
problem Generalization in noisy, out-of-distribution scenarios.
method Recurrent neural network guided by a Kalman filter.
result Recursive KalmanNet performs well in scenarios with different temporal dynamics from training data.
A new framework for efficient sequence maps using Bayesian filtering and covariance.
problem Designing efficient recurrent sequence maps from explicit memory assumptions.
method Design-model framework, exact Bayesian filtering, query-dependent readout, linear-Gaussian instantiation.
result Improved robustness and retrieval performance across various benchmarks.
A new deep approach to Kalman filtering integrates uncertainty estimates efficiently.
problem Integrating uncertainty estimates into deep time-series models.
method Proposes a Recurrent Kalman Network (RKN) that learns directly using backpropagation.
result RKN obtains more accurate uncertainty estimates and slightly improved prediction performance.
KalmanNet uses neural networks to improve state estimation in systems with unknown dynamics.
problem State estimation of systems with non-linear dynamics and partial information.
method KalmanNet integrates a recurrent neural network with the Kalman filter to handle non-linearities and model mismatches.
result KalmanNet outperforms classic filtering methods in systems with both mismatched and accurate domain knowledge.
We cast Amari's natural gradient in statistical learning as a specific case of Kalman filtering. Namely, applying an extended Kalman filter to estimate a fixed unknown parameter of a probabilistic model from a series of observations, is rigorously equivalent to estimating this parameter via an online stochastic natural…
Recurrent networks learn beliefs from history in partially observable environments.
problem Learning optimal policies in partially observable environments.
method Trained recurrent neural networks to approximate value functions, measuring mutual information between hidden states and beliefs.
result Recurrent networks' hidden states correlate with beliefs of relevant state variables, improving expected return.
Low dimensional representations of words allow accurate NLP models to be trained on limited annotated data. While most representations ignore words' local context, a natural way to induce context-dependent representations is to perform inference in a probabilistic latent-variable sequence model. Given the recent succes…
Regularized recurrent attention filter combines sensor inputs.
problem Combining information from different sensor modalities.
method Regularized recurrent attention filter, co-learning mechanism, probabilistic graphical model.
result Dynamic sensor fusion and latent representation recovery.
Neural Jump ODE improves continuous-time prediction and filtering of irregularly sampled time series.
problem Theoretical guarantees for continuous-time prediction and filtering of irregularly observed time series.
method Introducing Neural Jump ODE (NJ-ODE) that models conditional expectation between observations with neural ODEs and jumps.
result Theoretical guarantees for the L2-optimal prediction are provided, showing convergence of model output to optimal prediction. Process Mining consists of techniques where logs created by operative systems are transformed into process models. In process mining tools it is often desired to be able to classify ongoing process instances, e.g., to predict how long the process will still require to complete, or to classify process instances to diffe…
Deep learning framework for bond and yield curve forecasting with no-arbitrage constraints.
problem Arbitrage-free yield curve and bond price forecasting.
method Combines Kalman, extended Kalman, and particle filters with LSTM/CLSTM, and introduces AER term.
result Arbitrage regularization improves forecast accuracy, especially at short maturities.
DynaNet combines neural networks and SSMs for motion estimation and prediction.
problem Combining neural networks and SSMs for robust, interpretable motion estimation and prediction.
method Hybrid neural network and time-varying state-space model.
result State-of-the-art performance on challenging tasks like visual odometry and sensor fusion.
Improved electricity price forecasting model combining linear and non-linear structures.
problem Day-ahead electricity price forecasting in energy systems.
method Recurrent neural networks with embedded linear structures.
result Approximately 11% higher accuracy than state-of-the-art models.
Automatic sleep staging has been often treated as a simple classification problem that aims at determining the label of individual target polysomnography (PSG) epochs one at a time. In this work, we tackle the task as a sequence-to-sequence classification problem that receives a sequence of multiple epochs as input and…
Deep neural nets predict aircraft flight paths from weather data.
problem Accurate prediction of aircraft trajectories for aviation efficiency.
method Deep generative convolutional recurrent neural network with tree-based matching.
result Model accurately predicts aircraft flight paths from weather data.
Recurrent neural networks (RNNs) are a vital modeling technique that rely on internal states learned indirectly by optimization of a supervised, unsupervised, or reinforcement training loss. RNNs are used to model dynamic processes that are characterized by underlying latent states whose form is often unknown, precludi…
Randomized neural networks use fixed connections for efficiency.
problem Efficiency in deep learning models.
method Fixed connections in neural networks.
result Deep randomized neural networks achieve state-of-the-art results.
Adaptive vehicle trajectory prediction for safer autonomous driving.
problem Inability of current methods to guarantee physical feasibility and adapt to human driving policies.
method Bayesian recurrent neural network combining policy and physical models, with gradient-based training and parameter adaptation.
result The proposed method ensures physical feasibility and adaptability to human driving policies.
This paper proposes a method for generating speech from filterbank mel frequency cepstral coefficients (MFCC), which are widely used in speech applications, such as ASR, but are generally considered unusable for speech synthesis. First, we predict fundamental frequency and voicing information from MFCCs with an autoreg…
Enhances hedging strategies using deep neural networks.
problem Optimizing risks and returns in financial hedging.
method Integrates deep neural networks and random forest classifiers to find optimal hedging strategies.
result Improved hedging strategies with lower costs and risks.
Recurrent neural networks (RNNs) are types of artificial neural networks (ANNs) that are well suited to forecasting and sequence classification. They have been applied extensively to forecasting univariate financial time series, however their application to high frequency trading has not been previously considered. Thi…
In a variety of application domains the content to be recommended to users is associated with text. This includes research papers, movies with associated plot summaries, news articles, blog posts, etc. Recommendation approaches based on latent factor models can be extended naturally to leverage text by employing an exp…
New explanation of reservoir computing using random projections.
problem Understanding the randomness in reservoir computing.
method Constructing strongly universal reservoir systems as random projections of state-space systems.
result Approximation of any fading memory filters class by training a linear readout for each filter.
Variational autoencoders were proven successful in domains such as computer vision and speech processing. Their adoption for modeling user preferences is still unexplored, although recently it is starting to gain attention in the current literature. In this work, we propose a model which extends variational autoencoder…
We introduce the "NoBackTrack" algorithm to train the parameters of dynamical systems such as recurrent neural networks. This algorithm works in an online, memoryless setting, thus requiring no backpropagation through time, and is scalable, avoiding the large computational and memory cost of maintaining the full gradie…
We introduce Recurrent Predictive State Policy (RPSP) networks, a recurrent architecture that brings insights from predictive state representations to reinforcement learning in partially observable environments. Predictive state policy networks consist of a recursive filter, which keeps track of a belief about the stat…
We present Listen, Attend and Spell (LAS), a neural network that learns to transcribe speech utterances to characters. Unlike traditional DNN-HMM models, this model learns all the components of a speech recognizer jointly. Our system has two components: a listener and a speller. The listener is a pyramidal recurrent ne…
VSE estimates complex processes from noisy measurements without a model.
problem Estimating states of complex, model-free processes from noisy data.
method Variational state estimation using recurrent neural networks (RNNs) in both learning and inference phases.
result VSE provides a competitive state estimate for a benchmark process (Lorenz system) compared to known and data-driven methods.
Hybrid model combines graphical and learned inference for better data estimation.
problem Suboptimal estimation due to poor graphical model approximation of complex data generating process.
method Combines graphical inference with a learned inverse model structured as a graph neural network and formulated as a recurrent neural network.
result Hybrid model estimates chaotic trajectory more accurately than graphical or learned inference alone.
Recurrent neural networks improve time series forecasting accuracy.
problem Time series forecasting is challenging, especially for sequential data.
method A recurrent neural network framework for feature engineering, prediction, and evaluation is presented.
result The LSTM and GRU networks outperform traditional methods in forecasting accuracy.
A major hurdle to clinical translation of brain-machine interfaces (BMIs) is that current decoders, which are trained from a small quantity of recent data, become ineffective when neural recording conditions subsequently change. We tested whether a decoder could be made more robust to future neural variability by train…
Sequential Monte Carlo (SMC), or particle filtering, is a popular class of methods for sampling from an intractable target distribution using a sequence of simpler intermediate distributions. Like other importance sampling-based methods, performance is critically dependent on the proposal distribution: a bad proposal c…