Merge pull request #92 from innovationOUtside/wip

week 7 and housekeeping
innovationOUtside · Oct 7, 2020 · b1937e4 · b1937e4
2 parents 71f259c + 514f30e
commit b1937e4
Show file tree

Hide file tree

Showing 70 changed files with 3,676 additions and 2,395 deletions.
diff --git a/...ucing notebooks and the RoboLab environment/.md/01.3 Introducing nbev3devsim.md b/...ucing notebooks and the RoboLab environment/.md/01.3 Introducing nbev3devsim.md
@@ -68,7 +68,7 @@ Whilst the original `ev3devsim` simulator runs without any software requirements
 
 ## 3.2 The EV3 "brick"
 
-The Lego Mindstorms EV3 robotos that inspired `ev3dev`, `ev2devsim` and `nbev3devsim` are based around a physical EV3 controller with a 300 MHz ARM9 processor, 16 MB of Flash memory, 64 MB RAM and a Linux based operating system.
+The Lego Mindstorms EV3 robots that inspired `ev3dev`, `ev2devsim` and `nbev3devsim` are based around a physical EV3 controller with a 300 MHz ARM9 processor, 16 MB of Flash memory, 64 MB RAM and a Linux based operating system.
 
 ![figure ../tm129-19J-images/tm129_rob_p1_f005.jpg](../images/nogbad_ev3.jpg)
 
@@ -145,7 +145,7 @@ Click the *Run* button in the simulator to run the downloaded code there. The ro
 %%sim_magic_preloaded
 
 # Drive the robot forwards a short distance
-tank_drive.on(SpeedPercent(50), SpeedPercent(50))
+tank_drive.on_for_rotations(SpeedPercent(50), SpeedPercent(50), 2)
 tank_turn.on_for_rotations(-100, SpeedPercent(75), 2)
 ```
 

diff --git a/.../01. Introducing notebooks and the RoboLab environment/01.3 Introducing nbev3devsim.ipynb b/.../01. Introducing notebooks and the RoboLab environment/01.3 Introducing nbev3devsim.ipynb
@@ -76,7 +76,7 @@
    "source": [
     "## 3.2 The EV3 \"brick\"\n",
     "\n",
-    "The Lego Mindstorms EV3 robotos that inspired `ev3dev`, `ev2devsim` and `nbev3devsim` are based around a physical EV3 controller with a 300 MHz ARM9 processor, 16 MB of Flash memory, 64 MB RAM and a Linux based operating system.\n",
+    "The Lego Mindstorms EV3 robots that inspired `ev3dev`, `ev2devsim` and `nbev3devsim` are based around a physical EV3 controller with a 300 MHz ARM9 processor, 16 MB of Flash memory, 64 MB RAM and a Linux based operating system.\n",
     "\n",
     "![figure ../tm129-19J-images/tm129_rob_p1_f005.jpg](../images/nogbad_ev3.jpg)\n",
     "\n",
@@ -221,7 +221,7 @@
     "%%sim_magic_preloaded\n",
     "\n",
     "# Drive the robot forwards a short distance\n",
-    "tank_drive.on(SpeedPercent(50), SpeedPercent(50))\n",
+    "tank_drive.on_for_rotations(SpeedPercent(50), SpeedPercent(50), 2)\n",
     "tank_turn.on_for_rotations(-100, SpeedPercent(75), 2)"
    ]
   },
@@ -278,6 +278,18 @@
    "display_name": "Python 3",
    "language": "python",
    "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

diff --git a/...trolling program execution flow/.md/03.3 Program control flow using branches.md b/...trolling program execution flow/.md/03.3 Program control flow using branches.md
@@ -410,9 +410,9 @@ else:
 <!-- #endregion -->
 
 <!-- #region activity=true heading_collapsed=true -->
-#### Answer
+#### Example solution
 
-*Click the arrow in the sidebar or run this cell to reveal the answer.*
+*Click the arrow in the sidebar or run this cell to reveal an example solution.*
 <!-- #endregion -->
 
 <!-- #region activity=true hidden=true -->
@@ -453,9 +453,9 @@ How does the behaviour of the program lead to the robot’s emergent behaviour i
 <!-- #endregion -->
 
 <!-- #region activity=true heading_collapsed=true -->
-#### Discussion
+#### Example discussion
 
-*Click on the arrow in the sidebar or run this cell to reveal my observations*
+*Click on the arrow in the sidebar or run this cell to reveal an example discussion.*
 <!-- #endregion -->
 
 <!-- #region activity=true hidden=true -->

diff --git a/...ent/03. Controlling program execution flow/03.3 Program control flow using branches.ipynb b/...ent/03. Controlling program execution flow/03.3 Program control flow using branches.ipynb
@@ -640,9 +640,9 @@
     "heading_collapsed": true
    },
    "source": [
-    "#### Answer\n",
+    "#### Example solution\n",
     "\n",
-    "*Click the arrow in the sidebar or run this cell to reveal the answer.*"
+    "*Click the arrow in the sidebar or run this cell to reveal an example solution.*"
    ]
   },
   {
@@ -716,9 +716,9 @@
     "heading_collapsed": true
    },
    "source": [
-    "#### Discussion\n",
+    "#### Example discussion\n",
     "\n",
-    "*Click on the arrow in the sidebar or run this cell to reveal my observations*"
+    "*Click on the arrow in the sidebar or run this cell to reveal an example discussion.*"
    ]
   },
   {
@@ -1000,6 +1000,18 @@
    "display_name": "Python 3",
    "language": "python",
    "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.6"
   }
  },
  "nbformat": 4,

diff --git a/....md/04.1 Introducing program functions.md → ....md/04.1 Introducing program functions.md b/....md/04.1 Introducing program functions.md → ....md/04.1 Introducing program functions.md
diff --git a/... Robot navigation using dead reckoning.md → ... Robot navigation using dead reckoning.md b/... Robot navigation using dead reckoning.md → ... Robot navigation using dead reckoning.md
diff --git a/...robot behaviour and simple data charts.md → ...robot behaviour and simple data charts.md b/...robot behaviour and simple data charts.md → ...robot behaviour and simple data charts.md
diff --git a/...t robots/.md/04.4 Reasoning with Eliza.md → ...t robots/.md/04.4 Reasoning with Eliza.md b/...t robots/.md/04.4 Reasoning with Eliza.md → ...t robots/.md/04.4 Reasoning with Eliza.md
diff --git a/...04.5 Reasoning with rule based systems.md → ...04.5 Reasoning with rule based systems.md b/...04.5 Reasoning with rule based systems.md → ...04.5 Reasoning with rule based systems.md
diff --git a/.../04.1 Introducing program functions.ipynb → .../04.1 Introducing program functions.ipynb b/.../04.1 Introducing program functions.ipynb → .../04.1 Introducing program functions.ipynb
diff --git a/...bot navigation using dead reckoning.ipynb → ...bot navigation using dead reckoning.ipynb b/...bot navigation using dead reckoning.ipynb → ...bot navigation using dead reckoning.ipynb
diff --git a/...ot behaviour and simple data charts.ipynb → ...ot behaviour and simple data charts.ipynb b/...ot behaviour and simple data charts.ipynb → ...ot behaviour and simple data charts.ipynb
diff --git a/...nt robots/04.4 Reasoning with Eliza.ipynb → ...nt robots/04.4 Reasoning with Eliza.ipynb b/...nt robots/04.4 Reasoning with Eliza.ipynb → ...nt robots/04.4 Reasoning with Eliza.ipynb
diff --git a/...5 Reasoning with rule based systems.ipynb → ...5 Reasoning with rule based systems.ipynb b/...5 Reasoning with rule based systems.ipynb → ...5 Reasoning with rule based systems.ipynb
diff --git a/...4 Not quite intelligent robots/eliza.json → .... Not quite intelligent robots/eliza.json b/...4 Not quite intelligent robots/eliza.json → .... Not quite intelligent robots/eliza.json
diff --git a/.../04 Not quite intelligent robots/eliza.py → ...04. Not quite intelligent robots/eliza.py b/.../04 Not quite intelligent robots/eliza.py → ...04. Not quite intelligent robots/eliza.py
diff --git a/...te intelligent robots/nb_simple_speech.py → ...te intelligent robots/nb_simple_speech.py b/...te intelligent robots/nb_simple_speech.py → ...te intelligent robots/nb_simple_speech.py
diff --git a/.../05.1 Introducing sensor based control.md → .../05.1 Introducing sensor based control.md b/.../05.1 Introducing sensor based control.md → .../05.1 Introducing sensor based control.md
diff --git a/...ing with sensors/.md/05.2 Sensor noise.md → ...ing with sensors/.md/05.2 Sensor noise.md b/...ing with sensors/.md/05.2 Sensor noise.md → ...ing with sensors/.md/05.2 Sensor noise.md
diff --git a/.../05.3 The design engineer as detective.md → .../05.3 The design engineer as detective.md b/.../05.3 The design engineer as detective.md → .../05.3 The design engineer as detective.md
diff --git a/....md/05.4 Challenge - coping with noise.md → ....md/05.4 Challenge - coping with noise.md b/....md/05.4 Challenge - coping with noise.md → ....md/05.4 Challenge - coping with noise.md
diff --git a/...5.5 Experimenting with sensor settings.md → ...5.5 Experimenting with sensor settings.md b/...5.5 Experimenting with sensor settings.md → ...5.5 Experimenting with sensor settings.md
diff --git a/.../05.6 The RoboLab Grand Prix challenge.md → .../05.6 The RoboLab Grand Prix challenge.md b/.../05.6 The RoboLab Grand Prix challenge.md → .../05.6 The RoboLab Grand Prix challenge.md
diff --git a/....1 Introducing sensor based control.ipynb → ....1 Introducing sensor based control.ipynb b/....1 Introducing sensor based control.ipynb → ....1 Introducing sensor based control.ipynb
diff --git a/...ting with sensors/05.2 Sensor noise.ipynb → ...ting with sensors/05.2 Sensor noise.ipynb b/...ting with sensors/05.2 Sensor noise.ipynb → ...ting with sensors/05.2 Sensor noise.ipynb
diff --git a/....3 The design engineer as detective.ipynb → ....3 The design engineer as detective.ipynb b/....3 The design engineer as detective.ipynb → ....3 The design engineer as detective.ipynb
diff --git a/.../05.4 Challenge - coping with noise.ipynb → .../05.4 Challenge - coping with noise.ipynb b/.../05.4 Challenge - coping with noise.ipynb → .../05.4 Challenge - coping with noise.ipynb
diff --git a/... Experimenting with sensor settings.ipynb → ... Experimenting with sensor settings.ipynb b/... Experimenting with sensor settings.ipynb → ... Experimenting with sensor settings.ipynb
diff --git a/....6 The RoboLab Grand Prix challenge.ipynb → ....6 The RoboLab Grand Prix challenge.ipynb b/....6 The RoboLab Grand Prix challenge.ipynb → ....6 The RoboLab Grand Prix challenge.ipynb
diff --git a/...id_petl2po/authors/dev/cells/id_xhvf1c0/graffitis/id_ox4l2in/takes/id_g992ya7/history.txt b/...id_petl2po/authors/dev/cells/id_xhvf1c0/graffitis/id_ox4l2in/takes/id_g992ya7/history.txt
diff --git a/...e in the world are we/jupytergraffiti_data/notebooks/id_petl2po/authors/dev/manifest.json b/...e in the world are we/jupytergraffiti_data/notebooks/id_petl2po/authors/dev/manifest.json
diff --git a/....1 Introducing sensor based navigation.md → ....1 Introducing sensor based navigation.md b/....1 Introducing sensor based navigation.md → ....1 Introducing sensor based navigation.md
diff --git a/...in the world are we/.md/06.2 Runaround.md → ...in the world are we/.md/06.2 Runaround.md b/...in the world are we/.md/06.2 Runaround.md → ...in the world are we/.md/06.2 Runaround.md
diff --git a/... we/.md/06.3 Keeping track of distance.md → ... we/.md/06.3 Keeping track of distance.md b/... we/.md/06.3 Keeping track of distance.md → ... we/.md/06.3 Keeping track of distance.md
diff --git a/...we/.md/06.4 Keeping track of direction.md → ...we/.md/06.4 Keeping track of direction.md b/...we/.md/06.4 Keeping track of direction.md → ...we/.md/06.4 Keeping track of direction.md
diff --git a/...Introducing sensor based navigation.ipynb → ...Introducing sensor based navigation.ipynb b/...Introducing sensor based navigation.ipynb → ...Introducing sensor based navigation.ipynb
diff --git a/... in the world are we/06.2 Runaround.ipynb → ... in the world are we/06.2 Runaround.ipynb b/... in the world are we/06.2 Runaround.ipynb → ... in the world are we/06.2 Runaround.ipynb
diff --git a/...e we/06.3 Keeping track of distance.ipynb → ...e we/06.3 Keeping track of distance.ipynb b/...e we/06.3 Keeping track of distance.ipynb → ...e we/06.3 Keeping track of distance.ipynb
diff --git a/... we/06.4 Keeping track of direction.ipynb → ... we/06.4 Keeping track of direction.ipynb b/... we/06.4 Keeping track of direction.ipynb → ... we/06.4 Keeping track of direction.ipynb
diff --git a/...ent/07_Robot_Lab-WIP/.md/Section_00_01.md → ...s/.md/07.1 Introducing neural networks.md b/...ent/07_Robot_Lab-WIP/.md/Section_00_01.md → ...s/.md/07.1 Introducing neural networks.md
@@ -13,27 +13,30 @@ jupyter:
     name: python3
 ---
 
-# 1 Introduction
-
+# 1 Introducing neural networks
 
 You have already been introduced to neural networks in the study materials: now you are going to have an opportunity to play with them in practice.
 
 Neural networks can solve subtle pattern-recognition problems, which are very important in robotics. Although many of the activities are presented outside the robotics context, we will also try to show how they can be used to support robotics-related problems.
 
+In this session, you will get hands-on experience of using a variety of neural networks, and you will build and train neural networks to perform specific tasks, particularly in the area of image classification.
+
+
+# 1.1 Making sense of images
+
 In recent years, great advances have been made in generating powerful neural network-based models often referred to as ‘deep learning’ models. But neural networks have been around for over 50 years, with advances every few years, often reflecting advances in computing availability, and then long periods of ‘AI Winter’ when not much progress appeared to be being made.
 
 The following XKCD cartoon, [*Tasks*](https://xkcd.com/1425/), was first published in 2014. As is typical of XKCD cartoons, hovering over the cartoon reveals some hidden caption text. In this particular case: ‘_In the 60s, Marvin Minsky assigned a couple of undergrads to spend the summer programming a computer to use a camera to identify objects in a scene. He figured they'd have the problem solved by the end of the summer. Half a century later, we're still working on it_.’ 
 
-[![](../images//xkcd_tasks.png)](https://xkcd.com/1425/)
+[![](../images/xkcd_tasks.png)](https://xkcd.com/1425/)
 
 At the time (this is only a few short years ago, remember), recognising arbitrary items in images was still a hard task and the sentiment of this cartoon rang true. But within a few months, advances in neural network research meant that AI models capable of performing similar tasks, albeit crudely and with limited success, had started to appear. Today, photographs are routinely tagged with labels that identify what can be seen in the photograph using much larger, much more powerful, and much more effective AI models.
 
 However, identifying individual objects in an image on the one hand, and being able to generate a sensible caption that describes the image, is a different matter. A quick web search today will undoubtedly turn up some very enticing demos out there of automated caption generators. But ‘reading the scene’ presented by a picture and generating a caption from a set or keywords or tags associated with items that can be recognised in the image is an altogether more complex task: as well as performing the object recognition task correctly, we also need to be able to identify the relationships that exist between the different parts of the image; and do that in a meaningful way.
 
-In this session, you will get hands-on experience of using a variety of neural networks, and you will build and train neural networks to perform specific tasks.
 
 <!-- #region activity=true -->
-### Activity – Example image tagging demo
+### 1.1.1 Activity – Example image tagging demo
 
 There are many commercial image-tagging services available on the web that are capable of tagging uploaded images or images that can be identified by a web URL.
 
@@ -74,7 +77,7 @@ What risks, if any, might be associated with using such a service in each of tho
 <!-- #endregion -->
 
 <!-- #region activity=true -->
-### Activity – Recognising a static pose in an image
+### 1.1.2 Activity – Recognising a static pose in an image
 
 As well as tagging images, properly trained models can recognise individual people’s faces in photos (and not just of celebrities!) and human poses within a photograph.
 
@@ -83,7 +86,7 @@ Click through to the following web location to see an example of a neural networ
 <!-- #endregion -->
 
 
-## 1.1 Transfer learning
+## 1.2 Transfer learning
 
 Creating a neural network capable of recognising a particular image can take a lot of data and a lot of computing power. The training process typically involves showing the network being trained:
 
@@ -102,22 +105,11 @@ When you further train the model, it uses combinations of the features it can al
 
 
 <!-- #region activity=true -->
-## Optional activity – Distinguishing between two of your own poses from a live video feed
-Although it can take *a lot* of data and *a lot* of computational effort to train a model, topping up a model with transfer learning applied to a previously trained model can be achieved quite simply.
-
-This optional activity allows you to top-up a pre-trained model to recognise an image of you with your hand raised, and an image of you without you hand raised. Feeding a live image into the model allows it to detect in real time whether you have your hand or arm raised or not.
-
-__ TO DO _ need to package this as a jupyter_server_proxy thing.__
-__`demo-video-arm-pose` dir__
-
-*This activity requires that you have a camera attached to your computer and that your web browser has permission to access the camera feed. The captured images do not leave your computer.*
-<!-- #endregion -->
-
-<!-- #region activity=true -->
-## Optional activity – Training your own image or audio classifier
+### 1.2.1 Activity — Training your own image or audio classifier (optional)
 
+Although it can take *a lot* of data and *a lot* of computational effort to train a model, topping up a model with transfer learning applied to a previously trained model can be achieved quite simply.
 
-If you have a camera or microphone attached to your computer, then you can top-up a pre-trained model to distinguish between two or more categories of image or sound of your own devising. The [tutorial here](https://blog.google/technology/ai/teachable-machine/) describes a process for training a neural network to distinguish between images representing two different situations.
+In this (optional) activity, you can top-up a pre-trained model to distinguish between two or more categories of image or sound of your own devising. The [tutorial here](https://blog.google/technology/ai/teachable-machine/) describes a process for training a neural network to distinguish between images representing two different situations.
 
 You can train your own neural network by:
 
@@ -130,6 +122,6 @@ You can train your own neural network by:
 
 In this notebook you have seen how we can use a third-party application to recognise different objects within an image and return human-readable labels that can be used to ‘tag’ the image. These applications use large, pre-trained neural networks to perform the object-recognition task.
 
-You have also seen how we can take a pre-trained neural network model and use an approach called *transfer learning* to ‘top it up’ with a bit of extra learning so that it recognises particular sorts of differences between two classes of input image that we have provided it with.
+You have also been introduced to the idea that we can take a pre-trained neural network model and use an approach called *transfer learning* to ‘top it up’ with a bit of extra learning. This allows a network trained to distinguish items in one dataset to draw on that prior learning to recognise differences between additional categories of input image that we have provided it with.
 
 In the following notebooks you will have an opportunity to train your own neural network, from scratch, on a simple classification task.