minor changes

Author: fulcrum101

docs/logo.png renamed to docs/assets/logo.png

@@ -76,7 +76,7 @@
  {
  "cell_type": "markdown",
  "source": [
- "![NN in AI](slide_1.png)"
+ "![NN in AI](assets/slide_1.png)"
  ],
  "metadata": {
  "collapsed": false,
@@ -101,15 +101,15 @@
  "cell_type": "markdown",
  "source": [
  "The most popular problems/domains which NN algorithm solves are considered to be:\n",
- "![Most common NN problems](slide_2.png)\n",
+ "![Most common NN problems](assets/slide_2.png)\n",
  "* **Regression** - `the relationship estimate between dependent and independent variables.`\n",
  "> For example, you have different statistics about the house (f.i. bedroom number, has it garage or not, etc.) and you are required to estimate its price.\n",
  "> [More information](https://en.wikipedia.org/wiki/Regression_analysis)\n",
  "* **Computer Vision** - `derive meaniningful information from digital images, videos and other visual inputs.`\n",
  "> TLDR: allows computers to see, observe and understand.\n",
  "> For example, is it the image of dog or not?\n",
  "> [More information](https://www.ibm.com/topics/computer-vision)\n",
- "> ![Tweet](tweet.png)\n",
+ "> ![Tweet](assets/tweet.png)\n",
  "* **Natural Language Processing (NLP)** - `understand text and spoken words in much the same way human beings can.`\n",
  "> For example, is this email spam or not?\n",
  "> [More information](https://www.ibm.com/cloud/learn/natural-language-processing)\n",
@@ -140,8 +140,8 @@
  "cell_type": "markdown",
  "source": [
  "One of the most popular languages used for NN is Python, so in this workshop/tutorial we will be using it with libraries/packages associated with it.\n",
- "![Popular programming languages](slide_3.png)\n",
- "![Libraries](slide_4.png)\n",
+ "![Popular programming languages](assets/slide_3.png)\n",
+ "![Libraries](assets/slide_4.png)\n",
  "\n",
  "**Libraries/packages:**\n",
  "* **TensorFlow** - an end-to-end machine learning platform. Documentation [here](https://www.tensorflow.org/api_docs/python/tf)\n",
@@ -163,7 +163,7 @@
  "cell_type": "markdown",
  "source": [
  "Training ML models requires much computing power and often your computer don't have so much power to execute code. In that situation I recommend using free cloud-based Python code executors.\n",
- "![Execute code](slide_5.png)\n",
+ "![Execute code](assets/slide_5.png)\n",
  "* [**Google Colaboratory**](https://colab.research.google.com)\n",
  "* [**Kaggle**](https://www.kaggle.com)\n",
  "* [**Hugging faces**](https://huggingface.co/platform)"
@@ -180,7 +180,7 @@
  "source": [
  "## Neural Network structure - perceptron\n",
  "**Perceptron** can be considered as a neural networks basic *building block*.\n",
- "![Perceptron model](slide_6.png)\n",
+ "![Perceptron model](assets/slide_6.png)\n",
  "More information can be found [here](http://introtodeeplearning.com).\n",
  "\n",
  "Couple of stacked perceptron create *layers*. Layers that are not input or output are called *hidden layers*."

docs/slide_1.png renamed to docs/assets/slide_1.png

@@ -6,7 +6,7 @@ extra:
 
 theme:
  name: material
- logo: logo.png
+ logo: assets/logo.png
  icon:
  repo: fontawesome/brands/github
  features:
@@ -30,6 +30,9 @@ nav:
  - Part 2 Computer Visiom: part_2.ipynb
  - Useful links: useful_links.ipynb
 
+hide:
+ - navigation
+
 plugins:
  - search
  - mkdocs-jupyter: