The course is part of this learning path
This course focuses on machine learning. We're going to discuss what machine learning is and how we can leverage it to create intelligent and engaging apps. You'll also follow along as we create an image recognition app.
Hi, within this section, we're going to build an Image Recognition App. And in order to use this, we're going to use machine learning models. And of course before we do that, we have to learn what machine learning is and what the model is. In order to do that, let's go to developer.apple.com. And we're going to be searching some framework called Core ML. So, come over here to search bar and write Core ML, and you will see the first result that we're going to get is the Core ML, and this is a framework that lets us integrate machine learning models in our app. So, we're going to be seeing what this is. So, click on this 'Core ML' and we're going to see the documentation. So, actually in machine learning, we create models and we train these models to teach them about a subject. For example, we can create a model and teach that model how to recognize an image. Like if we show a monkey image to a model, it can say that, yes, this is probably a monkey, okay? And in this section, in fact, we're not going to be training models, were not going to be creating models, but we're going to use open source models to integrate our apps so that we can leverage this technique in order to create what we want. And if you want to learn further about training models, if you want to for learning about artificial intelligence or machine learning, I believe this is another cautious subject. Like maybe you want to work with Python, that's much more convenient programming language to work on machine learning models than Swift. But thanks to Apple, we can use those models in Swift in order to create some machine learning apps. So, in here we're going to create an Image Recognition App and we're going to do exactly what I've told you. We're going to show this model and monkey image and it will say, yes, this is probably a monkey, okay? So, if you come over this documentation, you will see some necessary first steps to take in order to create this kind of application. And in here you will see something like integrating a Core ML model into your app and getting a Core ML model and converting these models to Core ML framework, okay? And we're going to start by finding a related model for our app and they're actually good open source models. If you click over here to getting Core ML model, and in here you will see something like models, okay? And if you click on that, it will take you to this website, this is machine learning/models, okay? And don't worry, I'm going to upload this model to my GitHub account as well. You can download it from here. You can find the link at the end of the section, but I suggest you come over here and take a look at these models. For example, we have some image classification model in here called MobileNetV2 and we have other models as well, but we're going to be working with this one in this course. Like we have the SqueezeNet, we have this Restnet, they're all image classification models, okay? And we have other models here as well, like a drawing classification, but we're going to focus on this image classification. If you click over here, you will see some options of this model and we're going to see what these options stand for later on, but for right now know that we're going to be working with this MobileNetV2, and in fact you can work with other models like Restnet or SqueezeNet as well. They will all work in the way that I will show you because we're going to see how to work with a machine learning models in general, okay? So, that's what we're going to build in this section. Now, let's stop here and within the next lecture, we're going to start creating our app.
Atil is an instructor at Bogazici University, where he graduated back in 2010. He is also co-founder of Academy Club, which provides training, and Pera Games, which operates in the mobile gaming industry.