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.
Improves sequence modeling with a flow-based recurrent mixture density network.
This work introduces a new model for complex stochastic processes.
Neural networks predict traffic flow in smart cities.
RFN models urban mobility demand by separating temporal and spatial variability.
Gradient control plays an important role in feed-forward networks applied to various computer vision tasks. Previous work has shown that Recurrent Highway Networks minimize the problem of vanishing or exploding gradients. They achieve this by setting the eigenvalues of the temporal Jacobian to 1 across the time steps. …
Bayesian methods have been successfully applied to sparsify weights of neural networks and to remove structure units from the networks, e. g. neurons. We apply and further develop this approach for gated recurrent architectures. Specifically, in addition to sparsification of individual weights and neurons, we propose t…
This work combines recurrent models with diffusion for probabilistic time series forecasting.
Hybrid model predicts flow and pressure in water systems.
Recurrent Networks are one of the most powerful and promising artificial neural network algorithms to processing the sequential data such as natural languages, sound, time series data. Unlike traditional feed-forward network, Recurrent Network has a inherent feed back loop that allows to store the temporal context info…
BiHRNN predicts inflation by leveraging hierarchical structure and bidirectional RNNs.
The architecture of Transformer is based entirely on self-attention, and has been shown to outperform models that employ recurrence on sequence transduction tasks such as machine translation. The superior performance of Transformer has been attributed to propagating signals over shorter distances, between positions in …
A deep-learning-based surrogate model is developed and applied for predicting dynamic subsurface flow in channelized geological models. The surrogate model is based on deep convolutional and recurrent neural network architectures, specifically a residual U-Net and a convolutional long short term memory recurrent networ…
Short-term traffic flow prediction is one of the crucial issues in intelligent transportation system, which is an important part of smart cities. Accurate predictions can enable both the drivers and the passengers to make better decisions about their travel route, departure time and travel origin selection, which can b…
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…
Paper verifies RNNs using automata learning and model checking.
Deep RNNs excel at capturing long-term dependencies in sequential data.
Recurrent neural networks (RNNs) have been used extensively and with increasing success to model various types of sequential data. Much of this progress has been achieved through devising recurrent units and architectures with the flexibility to capture complex statistics in the data, such as long range dependency or l…
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain. Traffic forecasting is one canonical example of such learning task. The task is challenging due to (1) complex spatial dependency on road networks, (2) non-linear temporal dynamics with changing road conditions and (…
In this paper, we use variational recurrent neural network to investigate the anomaly detection problem on graph time series. The temporal correlation is modeled by the combination of recurrent neural network (RNN) and variational inference (VI), while the spatial information is captured by the graph convolutional netw…
The segmentation of the left ventricle (LV) from CINE MRI images is essential to infer important clinical parameters. Typically, machine learning algorithms for automated LV segmentation use annotated contours from only two cardiac phases, diastole, and systole. In this work, we present an analysis work-flow for fully-…
We prove quantitative recurrence and large deviations results for the Teichmuller geodesci flow on a connected component of a stratum of the moduli space of holomorphic unit-area quadratic differentials on a compact genus surface.
The horocyclic flow on geometrically infinite surfaces shows recurrent irregular orbits or non-minimal closures.
CTRNNs improve blood glucose forecasting in ICU, outperforming traditional models.
The study examines entropy and pressure at infinity in negatively curved manifolds, linking them to strong positive recurrence.
A3T-GCN improves traffic forecasting by capturing spatial and temporal dependencies.
The straight-line flow on almost every staircase and on almost every square tiled staircase is recurrent. For almost every square tiled staircase the set of periodic orbits is dense in the phase space.
TriTPP models enable faster and more flexible event data modeling.
Recurrent Neural Networks (RNNs) play a major role in the field of sequential learning, and have outperformed traditional algorithms on many benchmarks. Training deep RNNs still remains a challenge, and most of the state-of-the-art models are structured with a transition depth of 2-4 layers. Recurrent Highway Networks …
Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep reinforcement learning methods use recurrent neural networks (RNN) to memorize pas…
Hybrid model improves traffic flow prediction accuracy.
LSTMs and GRUs are the most common recurrent neural network architectures used to solve temporal sequence problems. The two architectures have differing data flows dealing with a common component called the cell state (also referred to as the memory). We attempt to enhance the memory by presenting a modification that w…
Attention mechanism combines bottom-up and top-down signals in neural networks.
The author shows that equicontinuous geodesic flows on surfaces are periodic. A similar result for flows on 3-manifolds is also proven. The idea of the proof is to show that the return map is recurrent and therefore periodic.
The study connects geodesic flows on Riemann surfaces to random walks on their dual graphs.
Interneurons improve learning in neural networks by accelerating convergence.
When sensors collect spatio-temporal data in a large geographical area, the existence of missing data cannot be escaped. Missing data negatively impacts the performance of data analysis and machine learning algorithms. In this paper, we study deep autoencoders for missing data imputation in spatio-temporal problems. We…
Traffic forecasting approaches are critical to developing adaptive strategies for mobility. Traffic patterns have complex spatial and temporal dependencies that make accurate forecasting on large highway networks a challenging task. Recently, diffusion convolutional recurrent neural networks (DCRNNs) have achieved stat…
New method reduces DSI complexity using RAE and LSTM for better posterior predictions.
New surfaces with special geodesic and horocycle behaviors discovered.
Extends Masur's divergence theorem to complex tori and Kummer surfaces.
Compact Recurrent Transformer (CRT) improves Transformer efficiency for long sequences.
We propose an approach that connects recurrent networks with different orders of hidden interaction with regular grammars of different levels of complexity. We argue that the correspondence between recurrent networks and formal computational models gives understanding to the analysis of the complicated behaviors of rec…
This work optimizes reservoir computing models by linking recurrence and non-linear dynamics.
Stable long-term predictions for fluid flows using neural networks.
Unrolled neural networks emerged recently as an effective model for learning inverse maps appearing in image restoration tasks. However, their generalization risk (i.e., test mean-squared-error) and its link to network design and train sample size remains mysterious. Leveraging the Stein's Unbiased Risk Estimator (SURE…
Stability is a fundamental property of dynamical systems, yet to this date it has had little bearing on the practice of recurrent neural networks. In this work, we conduct a thorough investigation of stable recurrent models. Theoretically, we prove stable recurrent neural networks are well approximated by feed-forward …
Wind energy resource quantification, air pollution monitoring, and weather forecasting all rely on rapid, accurate measurement of local wind conditions. Visual observations of the effects of wind---the swaying of trees and flapping of flags, for example---encode information regarding local wind conditions that can pote…
Gated recurrent neural networks have achieved remarkable results in the analysis of sequential data. Inside these networks, gates are used to control the flow of information, allowing to model even very long-term dependencies in the data. In this paper, we investigate whether the original gate equation (a linear projec…