Improving transferability for cross-domain trajectory prediction via neural stochastic differential equation

D Park, J Jeong, KJ Yoon - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
Multi-agent trajectory prediction is crucial for various practical applications, spurring the
construction of many large-scale trajectory datasets, including vehicles and pedestrians …

Spikeode: Image reconstruction for spike camera with neural ordinary differential equation

C Yang, G Li, S Wang, L Su, L Qing… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
The recently invented retina-inspired spike camera has shown great potential for capturing
dynamic scenes. However, reconstructing high-quality images from the binary spike data …

A Bidirectional Feedforward Neural Network Architecture Using the Discretized Neural Memory Ordinary Differential Equation.

H Niu, Z Yi, T He - International Journal of Neural Systems, 2024 - europepmc.org
Deep Feedforward Neural Networks (FNNs) with skip connections have revolutionized
various image recognition tasks. In this paper, we propose a novel architecture called …

Neural fractional order differential equations

SM Sivalingam, V Govindaraj - Expert Systems with Applications, 2025 - Elsevier
Neural ordinary differential equations are architectures that connect the neural network
theory with dynamical system, providing scope for continuous propagation of the layers …

PIDNODEs: Neural ordinary differential equations inspired by a proportional–integral–derivative controller

P Wang, S Chen, J Liu, S Cai, C Xu - Neurocomputing, 2025 - Elsevier
Abstract Neural Ordinary Differential Equations (NODEs) are a novel family of infinite-depth
neural-net models through solving ODEs and their adjoint equations. In this paper, we …

Laplace based Bayesian inference for ordinary differential equation models using regularized artificial neural networks

WM Kwok, G Streftaris, SC Dass - Statistics and Computing, 2023 - Springer
Parameter estimation and associated uncertainty quantification is an important problem in
dynamical systems characterised by ordinary differential equation (ODE) models that are …

Neural Multivariate Grey Model and Its Applications

Q Li, X Zhang - Applied Sciences, 2024 - mdpi.com
For time series forecasting, multivariate grey models are excellent at handling incomplete or
vague information. The GM (1, N) model represents this group of models and has been …

Continuous Depth Recurrent Neural Differential Equations

S Anumasa, G Gunapati, PK Srijith - Joint European Conference on …, 2023 - Springer
Recurrent neural networks (RNNs) have brought a lot of advancements in sequence
labeling tasks and sequence data. However, their effectiveness is limited when the …

A Review On Breaking the Limits of Time Series Forecasting Algorithms

A Raneez, T Wirasingha - 2023 IEEE 13th Annual Computing …, 2023 - ieeexplore.ieee.org
Time Series (TS) forecasting has stagnated owing to algorithm restrictions, therefore
systems developed using these methods can only perform so well. TS remains a challenge …

Using the Neural ODE Family to Predict the Number of Confirmed Cases in Taiwan

YL Zheng - 2022 - search.proquest.com
The number of confirmed COVID-19 cases in Taiwan has surged since mid-April 2022. We
aim to use past data to build a model to predict the number of confirmed cases in the future …