- Refer to this Alex Honchar's article or
NeuralODE_Alex_Honchar.htlm
- Refer to
NeuralODE_tutorial.ipynb
- Install jupyter notebook:
pip install jupyter
- Run jupyter notebook:
jupyter notebook
1. Create new env: conda create --name py38torch python=3.8
2. Active env: conda activate py38torch
4. Install torchdyn: pip install torchdyn==1.0.3
5. Install torch: conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia
==> Install 4, 5 in the end to avoid packages overwritten
-
Recommend to use conda to install packages for convenience
-
If you dont have GPU, please refer to Torch website for more details
- [Journal paper] Neural Ordinary Differential Equations
- [Presentation video] Neural Ordinary Differential Equations
- [Github] Tutorials and NeuralODE variants
- [Journal paper] Neural Controlled Differential Equations for Irregular Time Series
- [Presentation video] Neural Controlled Differential Equations for Irregular Time Series
- [Article] The Best Deep Learning Models for Time Series Forecasting
- [Article] DeepAR: Mastering Time-Series Forecasting with Deep Learning
- [Article] DeepAR: Mastering Time-Series Forecasting with Deep Learning
- [Python library] PyTorch Forecasting
- [Article] Time Series Forecasting with Neural Ordinary Differential Equations
- [Book chapter] Autonomous Underwater Vehicle Dynamics: Top priority
- [Book] HANDBOOK OF MARINE CRAFT HYDRODYNAMICS AND MOTION CONTROL
- [Book] Modelling and Control of Dynamic Systems Using Gaussian Process Model
- [Journal paper] Nonparametric modeling of ship maneuvering motion based on self-designed fully connected neural network
- [Journal paper] Identification and Prediction of Ship Maneuvering Motion Based on a Gaussian Process with Uncertainty Propagation
- [Journal paper] System identification of ship dynamic model based on Gaussian process regression with input noise
- Clear the cookies of your tab browser when you reach the limit of reading articles