chapter three (lesson four) (#131)

* Update README.md

* chapter 4 (lesson one)

3-transport/lessons/4-geofences/README.md

@@ -41,7 +41,7 @@ There are many reasons why you would want to know that a vehicle is inside or ou
 
 * Preparation for unloading - getting a notification that a vehicle has arrived on-site allows a crew to be prepared to unload the vehicle, reducing vehicle waiting time. This can allow a driver to make more deliveries in a day with less waiting time.
 * Tax compliance - some countries, such as New Zealand, charge road taxes for diesel vehicles based on the vehicle weight when driving on public roads only. Using geofences allows you to track the mileage driven on public roads as opposed to private roads on sites such as farms or logging areas.
-* Monitoring theft - if a vehicle should only remain in a certain area such as on a farm, and it leaves the geofence, it might be being stolen.
+* Monitoring theft - if a vehicle should only remain in a certain area such as on a farm, and it leaves the geofence, it might have been stolen.
 * Location compliance - some parts of a work site, farm or factory may be off-limits to certain vehicles, such as keeping vehicles that carry artificial fertilizers and pesticides away from fields growing organic produce. If a geofence is entered, then a vehicle is outside of compliance and the driver can be notified.
 
 ✅ Can you think of other uses for geofences?
@@ -212,7 +212,7 @@ For example, imagine GPS readings showing a vehicle was driving along a road tha
 
 ![A GPS trail showing a vehicle passing the Microsoft campus on the 520, with GPS readings along the road except for one on the campus, inside a geofence](../../../images/geofence-crossing-inaccurate-gps.png)
 
-In the above image, there is a geofence over part of the Microsoft campus. The red line shows a truck driving along the 520, with circles to show the GPS readings. Most of these are accurate and along the 520, with one inaccurate reading inside the geofence. The is no way that reading can be correct - there are no roads for the truck to suddenly divert from the 520 onto campus, then back onto the 520. The code that checks this geofence will need to take the previous readings into consideration before acting on the results of the geofence test.
+In the above image, there is a geofence over part of the Microsoft campus. The red line shows a truck driving along the 520, with circles to show the GPS readings. Most of these are accurate and along the 520, with one inaccurate reading inside the geofence. There is no way that reading can be correct - there are no roads for the truck to suddenly divert from the 520 onto campus, then back onto the 520. The code that checks this geofence will need to take the previous readings into consideration before acting on the results of the geofence test.
 
 ✅ What additional data would you need to check to see if a GPS reading could be considered correct?
 
@@ -237,7 +237,7 @@ In the above image, there is a geofence over part of the Microsoft campus. The r
 1. Use curl to make a GET request to this URL:
 
     ```sh
-    curl --request GET <URL>
+    curl --request GET '<URL>'
     ```
 
     > 💁 If you get a response code of `BadRequest`, with an error of:
@@ -255,7 +255,7 @@ In the above image, there is a geofence over part of the Microsoft campus. The r
         "geometries": [
             {
                 "deviceId": "gps-sensor",
-                "udId": "1ffb2047-6757-8c29-2c3d-da44cec55ff9",
+                "udId": "7c3776eb-da87-4c52-ae83-caadf980323a",
                 "geometryId": "1",
                 "distance": 999.0,
                 "nearestLat": 47.645875,

4-manufacturing/README.md

@@ -10,7 +10,7 @@ As advances happen in Artificial Intelligence (AI) and Machine Learning (ML), th
 
 In these 4 lessons you'll learn how to train image-based AI models to detect fruit quality, how to use these from an IoT device, and how to run these on the edge - that is on an IoT device rather than in the cloud.
 
-> 💁 These lessons will use some cloud resources. If you don't complete all the lessons in this project, make sure you [Clean up your project](../clean-up.md).
+> 💁 These lessons will use some cloud resources. If you don't complete all the lessons in this project, make sure you [clean up your project](../clean-up.md).
 
 ## Topics
 

4-manufacturing/lessons/1-train-fruit-detector/README.md

@@ -60,11 +60,11 @@ Traditional programming is where you take data, apply an algorithm to the data,
 
 ![Traditional development takes input and an algorithm and gives output. Machine learning uses input and output data to train a model, and this model can take new input data to generate new output](../../../images/traditional-vs-ml.png)
 
-Machine learning turns this around - you start with data and known outputs, and the machine learning tools work out the algorithm. You can then take that algorithm, called a *machine learning model*, and input new data and get new output.
+Machine learning turns this around - you start with data and known outputs, and the machine learning algorithm learns from the data. You can then take that trained algorithm, called a *machine learning model* or *model*, and input new data and get new output.
 
-> 🎓 The process of a machine learning tool generating a model is called *training*. The inputs and known outputs are called *training data*.
+> 🎓 The process of a machine learning algorithm learning from the data is called *training*. The inputs and known outputs are called *training data*.
 
-For example, you could give a model millions of pictures of unripe bananas as input training data, with the training output set as `unripe`, and millions of ripe banana pictures as training data with the output set as `ripe`. The ML tools will then generate a model. You then give this model a new picture of a banana and it will predict if the new picture is a ripe or an unripe banana.
+For example, you could give a model millions of pictures of unripe bananas as input training data, with the training output set as `unripe`, and millions of ripe banana pictures as training data with the output set as `ripe`. The ML algorithm will then create a model based off this data. You then give this model a new picture of a banana and it will predict if the new picture is a ripe or an unripe banana.
 
 > 🎓 The results of ML models are called *predictions*
 
@@ -122,6 +122,8 @@ To use Custom Vision, you first need to create two cognitive services resources
     Replace `<location>` with the location you used when creating the Resource Group.
 
     This will create a Custom Vision training resource in your Resource Group. It will be called `fruit-quality-detector-training` and use the `F0` sku, which is the free tier. The `--yes` option means you agree to the terms and conditions of the cognitive services.
+    
+> 💁 Use `S0` sku if you already have a free account using any of the Cognitive Services.
 
 1. Use the following command to create a free Custom Vision prediction resource: