 Hi, I'm Charlotte. And I'm here to talk about artificial intelligence. Last time we learned about recommender systems and data aggregators. How do those systems work? They work by AI sorting algorithms that help us to identify and match what we're looking for. Here's an example. Perhaps you want to listen to a podcast. And you've listened to several before. And the recommender system can recommend future podcasts that you might enjoy. We can also use AI sorting algorithms for health diagnoses and facial recognition. These AI sorting algorithms need to be both sensitive, so we don't skip important data, and specific, so that you don't find things that aren't there. So here's an example. Let's say that you want to search for dalmatians. These black and white dogs, right? A sensitive algorithm would find the dog on a white rug or find that small dog on a big fire truck. And a specific algorithm doesn't find cows. Doesn't find children in a dog costume. It doesn't find zebras. It just finds dalmatians. You can have a system that has false negatives and false positives. A false negative is when an item is defined as no match when it should be, such as if a sick person is told they're okay. A false positive is when an item is identified as a match and it is not, such as if a healthy person is told they're sick. Both false negatives and false positives are bad. For example, if we treat someone who's not sick, they may have pain and expense when they didn't need to. If we don't treat someone who is sick, then they may get sicker. So it's important that we refine these AI sorting algorithms to balance between the sensitive and the specific to eliminate both false negatives and false positives. And not everything is black and white. Usually we need results that are on a spectrum. So even in medicine or labeling that podcast that we wanna listen to, we need a balance of the algorithm finding, narrowing down what we need and a human deciding those final steps. Here's an example. Let's look at some pictures. What is swimming? Is it these kids in a competition? Is it kids playing at the beach? How about if they're riding on rafts? How about these surfers? What about water polo? How about this fish? Which of these would you label as swimming? We have to decide. It might be a spectrum. Maybe we're looking for a certain type of swimming. You can play with this crowdsource.google.com. Then we can explore more about AI sorting algorithms and how they're used for identification.