removing insecure URLs

Signed-off-by: Ranguelova Elena <[email protected]>

tutorials/XAI4ONNX_dianna_overview.ipynb

@@ -386,7 +386,8 @@
    "source": [
     "### Image example*\n",
     "\n",
-    "Here we apply the general workflow with image data from [Imagenet](https://image-net.org/download.php). The data item of interest is an image of a bee and we use the [ResNet 50](https://arxiv.org/abs/1512.03385) model trained on ImageNet to classify 1000 objects. We are interested in which pixels are contributing positively (red) and which - negatively (blue) towards the model's decision to classify the image as a 'bee' and we would like to use the [RISE](http://bmvc2018.org/contents/papers/1064.pdf) explainer:\n",
+    "Here we apply the general workflow with image data from Imagenet. The data item of interest is an image of a bee and we use the ResNet 50 model trained on ImageNet to classify 1000 objects. We are interested in which pixels are contributing positively (red) and which - negatively (blue) towards the model's decision to classify the image as a 'bee' and we would like to use the RISE, [Petsiuk et al., \"RISE: Randomized Input Sampling for Explanation of Black-box Models\", BMVC 2018].\n",
+    "  \n",
     "\n",
     "*For a full example see the [rise_imagenet](https://github.com/dianna-ai/dianna/blob/main/tutorials/explainers/RISE/rise_imagenet.ipynb) tutorial"
    ]
@@ -817,9 +818,7 @@
    "source": [
     "### Time series example*\n",
     "\n",
-    "Here we apply the general workflow on very simple time series (TS) data \n",
-    "<img width=\"25\" alt=\"Weather Logo\" src=\"https://github.com/dianna-ai/dianna/assets/3244249/3ff3d639-ed2f-4a38-b7ac-957c984bce9f\"> \n",
-    "representing daily temperatures with hot and cold days.  \n",
+    "Here we apply the general workflow on very simple time series (TS) data representing daily temperatures with hot and cold days.  \n",
     "We define a simple expert model that classifies the days to 'summer' or 'winter' based on a simple thresholding.\n",
     "We use RISE to explain the individual days' contributions to the model's decision. This illustrates that the explainers can work on any ML model and are not limited to neural networks.\n",
     "\n",
@@ -1539,7 +1538,7 @@
    "metadata": {},
    "source": [
     "## **Explainers**\n",
-    "DIANNA supports [LIME](https://www.kdd.org/kdd2016/papers/files/rfp0573-ribeiroA.pdf), [RISE](http://bmvc2018.org/contents/papers/1064.pdf) and [KernalSHAP](https://proceedings.neurips.cc/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf) XAI methods. It allows users to compare the outputs of three different explainers on the same model and data, illustrated best by [dianna's dashboard](https://github.com/dianna-ai/dianna#dashboard). This section briefly demonstrates how to run on the command line the supported explainers for the simple binary classification task of distinguishing the hand-written digits \"0\" and \"1\" on a test example from the Binary MNIST dataset, a subset of the [MNIST benchmark](http://yann.lecun.com/exdb/mnist/). It also gives the basics for each of the explainers."
+    "DIANNA supports **LIME**, [Ribeiro et al., \"Why Should I Trust You?: Explaining the Predictions of Any Classifier\", CoRR, 2016], **RISE**, [Petsiuk et al., \"RISE: Randomized Input Sampling for Explanation of Black-box Models\", BMVC 2018] and **KernalSHAP**, [Lundberg and Lee. ,\"A unified approach to interpreting model predictions.\", NIPS 2017] XAI methods. It allows users to compare the outputs of three different explainers on the same model and data, illustrated best by [dianna's dashboard](https://github.com/dianna-ai/dianna#dashboard). This section briefly demonstrates how to run on the command line the supported explainers for the simple binary classification task of distinguishing the hand-written digits \"0\" and \"1\" on a test example from the Binary MNIST dataset, a subset of the famous MNIST benchmark. It also gives the basics for each of the explainers."
    ]
   },
   {