diff --git a/11_deep_learning/01-Image-Restoration.ipynb b/11_deep_learning/01-Image-Restoration.ipynb
index 0364a8a..9c7d378 100644
--- a/11_deep_learning/01-Image-Restoration.ipynb
+++ b/11_deep_learning/01-Image-Restoration.ipynb
@@ -16,7 +16,7 @@
     "\n",
     ">conda create -n 'dl-biapol' python=3.7  \n",
     "conda activate dl-biapol  \n",
-    "pip install tensorflow-gpu=2.4.1 keras=2.3.1 n2v jupyter  scikit-image gputools\n",
+    "pip install tensorflow-gpu==2.4.1 keras==2.3.1 n2v jupyter  scikit-image gputools\n",
     "\n",
     "Finally open this notebook using `jupyter notebook`\n",
     "\n",
diff --git a/11_deep_learning/02-Image-Semantic-Segmentation.ipynb b/11_deep_learning/02-Image-Semantic-Segmentation.ipynb
index bf8a876..62a3b1e 100644
--- a/11_deep_learning/02-Image-Semantic-Segmentation.ipynb
+++ b/11_deep_learning/02-Image-Semantic-Segmentation.ipynb
@@ -2,15 +2,15 @@
  "cells": [
   {
    "cell_type": "markdown",
-   "id": "df043420",
+   "id": "61a163c8",
    "metadata": {},
    "source": [
-    "### This notebook is adapted from https://github.com/dl4mia/04_instance_segmentation/blob/main/1_semantic_segmentation_2D.ipynb"
+    "### This notebook is adapted from **https://github.com/dl4mia/04_instance_segmentation/blob/main/1_semantic_segmentation_2D.ipynb**"
    ]
   },
   {
    "cell_type": "markdown",
-   "id": "f42b61ff",
+   "id": "8d8bb293",
    "metadata": {},
    "source": [
     "In this notebook, we will perform pixel-wise segmentation or <i> semantic segmentation </i> on some microscopy images using a standard model architecture called the U-Net.  \n",
@@ -24,7 +24,7 @@
     "\n",
     ">conda create -n 'dl-biapol' python=3.7  \n",
     "conda activate dl-biapol  \n",
-    "pip install tensorflow-gpu=2.4.1 keras=2.3.1 n2v jupyter  scikit-image gputools\n",
+    "pip install tensorflow-gpu==2.4.1 keras==2.3.1 n2v jupyter  scikit-image gputools\n",
     "\n",
     "Finally open this notebook using `jupyter notebook`\n",
     "\n",
@@ -37,7 +37,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3c078f0c",
+   "id": "aae6c93c",
    "metadata": {},
    "source": [
     "### Get Dependencies"
@@ -46,7 +46,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "88cf29aa",
+   "id": "787ee718",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -71,7 +71,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "22059655",
+   "id": "eaa7d193",
    "metadata": {},
    "source": [
     "### Data"
@@ -79,7 +79,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "62cdd825",
+   "id": "2f491c62",
    "metadata": {},
    "source": [
     "> First we download some sample images and corresponding masks"
@@ -88,7 +88,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "0b96ab62",
+   "id": "880568ef",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -103,7 +103,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "57af5782",
+   "id": "2f8365a6",
    "metadata": {},
    "source": [
     "> Next we load the data, generate from the annotation masks background/foreground/cell border masks, and crop out a central patch (this is just for simplicity, as it makes our life a bit easier when all images have the same shape)\n"
@@ -112,7 +112,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "652b1f9c",
+   "id": "b7eadac0",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -140,7 +140,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d92f9390",
+   "id": "5ddf35bf",
    "metadata": {},
    "source": [
     "<div class=\"alert alert-block alert-info\"> Q:<b> What does <u>one-hot</u> parameter in the <i>to_3class_label</i> function imply? </b>.<br>\n",
@@ -149,7 +149,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8380363d",
+   "id": "ada06194",
    "metadata": {},
    "source": [
     "> Plot an example image"
@@ -158,7 +158,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4be38ec6",
+   "id": "1aaf08dc",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -174,7 +174,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "04790b83",
+   "id": "bbda6ec7",
    "metadata": {},
    "source": [
     "<div class=\"alert alert-block alert-info\"> Q:<b> Plot some more images. What kind of data is shown? How variable is it? Do the segmentation masks look reasonable?  </b>.<br>\n",
@@ -183,7 +183,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "d5218dc1",
+   "id": "87a7fd5d",
    "metadata": {},
    "source": [
     "> We now split the training data into ~ 80/20 training and validation data"
@@ -192,7 +192,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "12418fa0",
+   "id": "5839b26f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -215,7 +215,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "bee6ea5e",
+   "id": "4c07ff28",
    "metadata": {},
    "source": [
     "> We now will construct a very simple 3-class segmentation model, for which we will use a UNet"
@@ -224,7 +224,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f7d22f6f",
+   "id": "76bbfc4f",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -237,7 +237,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "3b608d93",
+   "id": "9dd9c3ab",
    "metadata": {},
    "source": [
     "<div class=\"alert alert-block alert-info\"> Q:<b> What is the intuition behind the <u>skip connections</u> in a U-Net? </b> <br>\n",
@@ -248,7 +248,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "9f4cd8c3",
+   "id": "ba979c13",
    "metadata": {},
    "source": [
     "### Training the model"
@@ -256,7 +256,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "0efb7625",
+   "id": "a5d2df1a",
    "metadata": {},
    "source": [
     "> We now will compile the model, i.e. deciding on a loss function and an optimizer.  \n",
@@ -267,7 +267,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "e4a8f340",
+   "id": "815eeb88",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -276,7 +276,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "df168f33",
+   "id": "fd9f4ca3",
    "metadata": {},
    "source": [
     "> Before we train the model, we define some callbacks that will monitor the training loss etc"
@@ -285,7 +285,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a409f9b8",
+   "id": "528db37e",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -304,7 +304,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "4975ba35",
+   "id": "b1bf7e60",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -314,7 +314,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "8aa07946",
+   "id": "d1dc9762",
    "metadata": {},
    "source": [
     "### Prediction on unseen data"
@@ -323,7 +323,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "7ab81b7d",
+   "id": "3c614d67",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -337,7 +337,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "5445d7b6",
+   "id": "3cbb2fa3",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -348,7 +348,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "51684a40",
+   "id": "53e32506",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -373,7 +373,7 @@
   },
   {
    "cell_type": "markdown",
-   "id": "391387aa",
+   "id": "7a183229",
    "metadata": {},
    "source": [
     "<div class=\"alert alert-block alert-info\"> Q:<b> Can you spot the label image mistakes? </b> </div>"
@@ -382,7 +382,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "a9d251f8",
+   "id": "eb4d56f3",
    "metadata": {},
    "outputs": [],
    "source": []
@@ -390,7 +390,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "f1753517",
+   "id": "72786feb",
    "metadata": {},
    "outputs": [],
    "source": []
diff --git a/11_deep_learning/Slides.pdf b/11_deep_learning/Slides.pdf
new file mode 100644
index 0000000..759a7be
Binary files /dev/null and b/11_deep_learning/Slides.pdf differ