diff --git a/README.md b/README.md
index aa35911f..a672e3b7 100644
--- a/README.md
+++ b/README.md
@@ -196,7 +196,7 @@ explanation = dianna.explain_timeseries(model_path, timeseries_data=timeseries_i
```
-For visualization of the heatmap please refer to the [tutorial](https://github.com/dianna-ai/dianna/blob/main/tutorials/lime_timeseries_coffee.ipynb)
+For visualization of the heatmap please refer to the [tutorial](https://github.com/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_timeseries_coffee.ipynb)
### Tabular example:
@@ -216,6 +216,10 @@ plot_tabular(explanation, X_test.columns, num_features=10) # display 10 most sa
+### IMPORTANT: Sensitivity to hyperparameters
+The XAI methods (explainers) are sensitive to the choice of their hyperparameters! In this [work](https://staff.fnwi.uva.nl/a.s.z.belloum/MSctheses/MScthesis_Willem_van_der_Spec.pdf), this sensitivity to hyperparameters is researched and useful conclusions are drawn.
+The default hyperparameters used in DIANNA for each explainer as well as the values for our tutorial examples are given in the Tutorials [README](./tutorials/README.md#important-hyperparameters).
+
## Dashboard
Explore the explanations of your trained model using the DIANNA dashboard (for now images, text and time series classification is supported).
@@ -305,7 +309,7 @@ And here are links to notebooks showing how we created our models on the benchma
## Tutorials
-DIANNA supports different data modalities and XAI methods. The table contains links to the relevant XAI method's papers (for some explanatory videos on the methods, please see [tutorials](./tutorials)). The DIANNA [tutorials](./tutorials) cover each supported method and data modality on a least one dataset. Our future plans to expand DIANNA with more data modalities and XAI methods are given in the [ROADMAP](https://dianna.readthedocs.io/en/latest/ROADMAP.html).
+DIANNA supports different data modalities and XAI methods. The table below contains links to the relevant XAI method's papers (for some explanatory videos on the methods, please see [tutorials](./tutorials)). The DIANNA [tutorials](./tutorials) cover each supported method and data modality on a least one dataset using the default or tuned [hyperparameters](./tutorials/README.md#important-hyperparameters). Our future plans to expand DIANNA with more data modalities and XAI methods are given in the [ROADMAP](https://dianna.readthedocs.io/en/latest/ROADMAP.html).
diff --git a/tutorials/README.md b/tutorials/README.md
index deb1a693..1013b16e 100644
--- a/tutorials/README.md
+++ b/tutorials/README.md
@@ -10,36 +10,61 @@ pip install .[notebooks]
For *general demonstration of DIANNA* click on the logo [
](https://github.com/dianna-ai/dianna/blob/main/tutorials/demo.ipynb) or run it in Colab: [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/demo.ipynb).
-For *tutorials on how to convert* an [Keras](https://keras.io/), [PyTorch](https://pytorch.org/), [Scikit-learn](https://scikit-learn.org/stable/) or [Tensorflow](https://www.tensorflow.org/) model to [ONNX](https://onnx.ai/), please see the [conversion tutorials](https://github.com/dianna-ai/dianna/blob/main/tutorials/conversion_onnx/).
+For *tutorials on how to convert* an [Keras](https://keras.io/), [PyTorch](https://pytorch.org/), [Scikit-learn](https://scikit-learn.org/stable/) or [Tensorflow](https://github.com/tensorflow/) model to [ONNX](https://onnx.ai/), please see the [conversion tutorials](https://github.com/dianna-ai/dianna/blob/main/tutorials/conversion_onnx/).
For *specific XAI methods (explainers)*:
* Click on the explainer names to watch explanatory videos for the respective method.
* Click on the logos below for direct access to a tutorial notebook for a combination of explainer and data modality/dataset.
-Run the tutorials directly in Google Colab by clicking on the Colab buttons below:
+The **datasets** and the **tasks** used in the tutorials are represented with their respective logos:
+|*Data modality*|Dataset|*Task*|Logo|
+|:------------|:------|:---|:----|
+|*Images*|Binary MNIST | Binary digit *classification*| 
|
+||[Simple Geometric (circles and triangles)](https://doi.org/10.5281/zenodo.5012824)| Binary shape *classificaiton* |
|
+||[Simple Scientific (LeafSnap30)](https://zenodo.org/record/5061353/)| $30$ tree species leaves *classification* | 
|
+||[Imagenet](https://image-net.org/download.php) |$1000$ classes natural images *classificaiton* | 
|
+|*Text*| [Stanford sentiment treebank](https://nlp.stanford.edu/sentiment/index.html) |Positive or negative movie reviews sentiment *classificaiton* | 
|
+|*Timeseries* | [Coffee dataset](https://timeseriesclassification.com/description.php?Dataset=Coffee) | Binary *classificaiton* of Robusta and Aribica coffee beans| 
|
+| | [Weather dataset](https://zenodo.org/record/7525955) |Binary *classification* (summer/winter) of temperature time-series |
|
+| | Fast Radio Burst (FRB) dataset (not publicly available) | Binary *classificaiton* of Fast Radio Burst (FRB) timeseries data : noise or a real FRB. | 
|
+|*Tabular*| [Penguin dataset](https://www.kaggle.com/code/parulpandey/penguin-dataset-the-new-iris)| $3$ penguin spicies (Adele, Chinstrap, Gentoo) *classificaiton* | 
| |
+| | [Weather dataset](https://zenodo.org/record/7525955) | Next day sunshine hours prediction (*regression*) | |
+
+The **ONNX models** used in the tutorials are available at [dianna/models](https://github.com/dianna-ai/dianna/tree/main/dianna/models), or linked from their respective tutorial notebooks.
+
+Run the **tutorials** directly in Google Colab by clicking on the Colab buttons below:
|*Modality* \ Method|RISE|[LIME](https://youtu.be/d6j6bofhj2M)|Kernel[SHAP](https://youtu.be/9haIOplEIGM)|
|:-----|:---|:---|:---|
-|*Images*|[](/explainers/RISE/rise_mnist.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_mnist.ipynb) | [](/explainers/LIME/lime_images.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_images.ipynb) | [](/explainers/KernelSHAP/kernelshap_mnist.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/KernelSHAP/kernelshap_mnist.ipynb) |
-| | [](/explainers/RISE/rise_imagenet.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_imagenet.ipynb) | | [](/explainers/KernelSHAP/kernelshap_geometric_shapes.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/KernelSHAP/kernelshap_geometric_shapes.ipynb)|
-|*Text* |[](/explainers/RISE/rise_text.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_text.ipynb) |[](/explainers/LIME/lime_text.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_text.ipynb) |[]()|
-| *Time series*| [
](/explainers/RISE/rise_timeseries_weather.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_timeseries_weather.ipynb)| [](/explainers/LIME/lime_timeseries_weather.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_timeseries_weather.ipynb)| |
-| | [](rise_timeseries_frb.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_timeseries_frb.ipynb) | [
](/explainers/LIME/lime_timeseries_coffee.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_timeseries_coffee.ipynb) | |
-| *Tabular* | | [](/explainers/LIME/lime_tabular_penguin.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_tabular_penguin.ipynb) | |
-| | | [](/explainers/LIME/lime_tabular_weather.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_tabular_weather.ipynb)| |
-
-The datasets used in the tutorials are represented with their respective logos:
-|Data modality|Dataset|Logo|
-|:------------|:------|:---|
-|*Images*|Binary MNIST | |
-||[Simple Geometric (circles and triangles)](https://doi.org/10.5281/zenodo.5012824)| |
-||[Simple Scientific (LeafSnap30)](https://zenodo.org/record/5061353/)| |
-||[Imagenet](https://image-net.org/download.php) | |
-|*Text*| [Stanford sentiment treebank](https://nlp.stanford.edu/sentiment/index.html) | |
-|*Timeseries* | [Coffee dataset](https://timeseriesclassification.com/description.php?Dataset=Coffee) | |
-| | [Weather dataset](https://zenodo.org/record/7525955) | |
-| | FRB dataset (not publicly available) | |
-|*Tabular*| [Penguin dataset](https://www.kaggle.com/code/parulpandey/penguin-dataset-the-new-iris)| | |
-| | [Weather dataset](https://zenodo.org/record/7525955) | |
-
-The ONNX models used in the tutorials are available at [dianna/models](https://github.com/dianna-ai/dianna/tree/main/dianna/models), or linked from their respective tutorial notebooks.
+|*Images*|[](./explainers/RISE/rise_mnist.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_mnist.ipynb) | [](./explainers/LIME/lime_images.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_images.ipynb) | [](./explainers/KernelSHAP/kernelshap_mnist.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/KernelSHAP/kernelshap_mnist.ipynb) |
+| | [](./explainers/RISE/rise_imagenet.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_imagenet.ipynb) | | [](./explainers/KernelSHAP/kernelshap_geometric_shapes.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/KernelSHAP/kernelshap_geometric_shapes.ipynb)|
+|*Text* |[](./explainers/RISE/rise_text.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_text.ipynb) |[](./explainers/LIME/lime_text.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_text.ipynb) |[]()|
+| *Time series*| [](./explainers/RISE/rise_timeseries_weather.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_timeseries_weather.ipynb)| [](./explainers/LIME/lime_timeseries_weather.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_timeseries_weather.ipynb)| |
+| | [](./explainers/RISE/rise_timeseries_frb.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_timeseries_frb.ipynb) | [](./explainers/LIME/lime_timeseries_coffee.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_timeseries_coffee.ipynb) | |
+| *Tabular* | | [](./explainers/LIME/lime_tabular_penguin.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_tabular_penguin.ipynb) | |
+| | | [](./explainers/LIME/lime_tabular_weather.ipynb) or [](https://colab.research.google.com/github/dianna-ai/dianna/blob/main/tutorials/explainers/LIME/lime_tabular_weather.ipynb)| |
+
+
+### IMPORTANT: Hyperparameters
+The XAI methods (explainers) are sensitive to the choice of their hyperparameters! In this [master Thesis](https://staff.fnwi.uva.nl/a.s.z.belloum/MSctheses/MScthesis_Willem_van_der_Spec.pdf), this sensitivity is researched and useful conclusions are drawn.
+The default hyperparameters used in DIANNA for each explainer as well as the choices for some tutorials and their data modality (*i* - images, *txt* - text, *ts* - time series and *tab* - tabular) are given below:
+
+#### RISE
+| Hyperparameter | Default value | (*i*)| (*i*) | (*txt*) | (*ts*)| (*ts*)|
+| ------------- | ------------- | -------------------|-----------------------------| ---------------------------------|---------------------------------|---------------------------------|
+| $n_{masks}$ |**$1000$** | default | $5000$ | default | $10000$ |$5000$ |
+| $p_{keep}$ | **optimized** (*i*, *txt*), **$0.5$** (*ts*) | $0.1$| $0.1$ | default | $0.1$| $0.1$|
+| $n_{features}$ |**$8$** | $6$ |default | default | default | $16$ |
+#### LIME
+| Hyperparameter | Default value | (*i*) | (*ts*)| (*ts*)|
+| ------------- | ------------- |--------| -----| -----|
+| $n_{samples}$ | **$5000$** | $1000$ | $10 000$| $500$|
+| Kernel Width | **$25$**| default | default| default|
+| $n_{features}$ | **$10$** | $30$ | default| default|
+
+#### KernalSHAP
+| Hyperparameter | Default value | (*i*)| (*i*)|
+| ------------- | ------------- |------------- |------------- |
+| $n_{samples}$ | **auto/int** | $1000$| $2000$ |
+| $n_{segments}$ | **$100$** |$200$ |$200$ |
+