Improving transferability for cross-domain trajectory prediction via neural stochastic differential equation
Multi-agent trajectory prediction is crucial for various practical applications, spurring the
construction of many large-scale trajectory datasets, including vehicles and pedestrians …
construction of many large-scale trajectory datasets, including vehicles and pedestrians …
Spikeode: Image reconstruction for spike camera with neural ordinary differential equation
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 …
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.
Deep Feedforward Neural Networks (FNNs) with skip connections have revolutionized
various image recognition tasks. In this paper, we propose a novel architecture called …
various image recognition tasks. In this paper, we propose a novel architecture called …
Neural fractional order differential equations
Neural ordinary differential equations are architectures that connect the neural network
theory with dynamical system, providing scope for continuous propagation of the layers …
theory with dynamical system, providing scope for continuous propagation of the layers …
PIDNODEs: Neural ordinary differential equations inspired by a proportional–integral–derivative controller
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 …
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
Parameter estimation and associated uncertainty quantification is an important problem in
dynamical systems characterised by ordinary differential equation (ODE) models that are …
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 …
vague information. The GM (1, N) model represents this group of models and has been …
Continuous Depth Recurrent Neural Differential Equations
Recurrent neural networks (RNNs) have brought a lot of advancements in sequence
labeling tasks and sequence data. However, their effectiveness is limited when the …
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 …
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 …
aim to use past data to build a model to predict the number of confirmed cases in the future …