@@ -4,7 +4,12 @@ This semester project (SP) focuses on "A first exploration of the new minGRU mod
## Detailed Assignment Description
As part of this assignment, implement in PyTorch a minGRU architecture following the specifications from [Feng et al. (2024)](https://arxiv.org/abs/2410.01201).
We perform a first exploration of the potential of the recently-introduced minGRU models for parameter inference and forecasting in time-series. (The finer details of the results can be added after the results are finalised). (More detailed assignment description to be provided later.)
We perform a first exploration of the potential of the recently-introduced minGRU models for parameter inference and forecasting in time series. Which consists of three tasks:
1. Parameter inference of sinusoidal waves
2. Time series forecasting on sinusoidal waves
3. Time series forecasting on market stock data
(The finer details of the results can be added after the results are finalised). (More detailed assignment description to be provided later.)
## Dataset Information
The dataset required for this project is generated programmatically. Therefore, there is no need to download any external datasets. (As of the current state of the project)
...
...
@@ -26,9 +31,19 @@ To run this project, you will need the following dependencies:
mingru_notebook_param_infer.ipynb
```
- Run the following Jupyter notebook for time series forecasting:
- Run the following Jupyter notebook for time series forecasting of sinusoidal waves:
```sh
mingru_notebook_forecasting.ipynb
```
This notebook also contains code for loading models from "trained_models" directory.
\ No newline at end of file
This notebook also contains code for loading models from "trained_models" directory.
- Run the following Jupyter notebook for minGRU time series forecasting of stock data:
```sh
stock_data_mingru.ipynb
```
- Run the following Jupyter notebook for DARTS models time series forecasting of stock data:
