Library

Course: Complete iOS 11 Machine Learning Masterclass

Complete iOS 11 Machine Learning Masterclass

Description

If you want to learn how to start building professional, career-boosting mobile apps and use Machine Learning to take things to the next level, then this course is for you. The Complete iOS Machine Learning Masterclass™ is the only course that you need for machine learning on iOS. Machine Learning is a fast-growing field that is revolutionizing many industries with tech giants like Google and IBM taking the lead. In this course, you’ll use the most cutting-edge iOS Machine Learning technology stacks to add a layer of intelligence and polish to your mobile apps. We’re approaching a new era where only apps and games that are considered “smart” will survive. (Remember how Blockbuster went bankrupt when Netflix became a giant?) Jump the curve and adopt this innovative approach; the Complete iOS Machine Learning Masterclass™ will introduce Machine Learning in a way that’s both fun and engaging.

In this course, you will:

  • Master the 3 fundamental branches of applied Machine Learning: Image & Video Processing, Text Analysis, and Speech & Language Recognition
  • Develop an intuitive sense for using Machine Learning in your iOS apps
  • Create 7 projects from scratch in practical code-along tutorials
  • Find pre-trained ML models and make them ready to use in your iOS apps
  • Create your own custom models
  • Add Image Recognition capability to your apps
  • Integrate Live Video Camera Stream Object Recognition to your apps
  • Add Siri Voice speaking feature to your apps
  • Dive deep into key frameworks such as coreML, Vision, CoreGraphics, and GamePlayKit.

  • Use Python, Keras, Caffee, Tensorflow, sci-kit learn, libsvm, Anaconda, and Spyder–even if you have zero experience
  • Get FREE unlimited hosting for one year
  • And more!

This course is also full of practical use cases and real-world challenges that allow you to practice what you’re learning. Are you tired of courses based on boring, over-used examples? Yes? Well then, you’re in a treat. We’ll tackle 5 real-world projects in this course so you can master topics such as image recognition, object recognition, and modifying existing trained ML models. You’ll also create an app that classifies flowers and another fun project inspired by Silicon Valley Jian Yang’s masterpiece: a Not-Hot Dog classifier app! 

Why Machine Learning on iOS

One of the hottest growing fields in technology today, Machine Learning is an excellent skill to boost your your career prospects and expand your professional tool kit. Many of Silicon Valley’s hottest companies are working to make Machine Learning an essential part of our daily lives. Self-driving cars are just around the corner with millions of miles of successful training. IBM’s Watson can diagnose patients more effectively than highly-trained physicians. AlphaGo, Google DeepMind’s computer, can beat the world master of the game Go, a game where it was thought only human intuition could excel.

In 2017, Apple has made Machine Learning available in iOS 11 so that anyone can build smart apps and games for iPhones, iPads, Apple Watches and Apple TVs. Nowadays, apps and games that do not have an ML layer will not be appealing to users. Whether you wish to change careers or create a second stream of income, Machine Learning is a highly lucrative skill that can give you an amazing sense of gratification when you can apply it to your mobile apps and games.

Why This Course Is Different

Machine Learning is very broad and complex; to navigate this maze, you need a clear and global vision of the field. Too many tutorials just bombard you with the theory, math, and coding. In this course, each section focuses on distinct use cases and real projects so that your learning experience is best structured for mastery.

This course brings my teaching experience and technical know-how to you. I’ve taught programming for over 10 years, and I’m also a veteran iOS developer with hands-on experience making top-ranked apps. For each project, we will write up the code line by line to create it from scratch. This way you can follow along and understand exactly what each line means and how to code comes together. Once you go through the hands-on coding exercises, you will see for yourself how much of a game-changing experience this course is.

As an educator, I also want you to succeed. I’ve put together a team of professionals to help you master the material. Whenever you ask a question, you will get a response from my team within 48 hours. No matter how complex your question, we will be there–because we feel a personal responsibility in being fully committed to our students.

By the end of the course, you will confidently understand the tools and techniques of Machine Learning for iOS on an instinctive level.

Don’t be the one to get left behind. Get started today and join millions of people taking part in the Machine Learning revolution.

topics: ios 11 swift 4 coreml vision deep learning machine learning neural networks python anaconda trained models keras tensorflow scikit learn core ml ios11 Swift4 scikitlearn artificial neural network ANN recurrent neural network RNN convolutional neural network CNN ocr character recognition face detection ios 11 swift 4 coreml vision deep learning machine learning neural networks python anaconda trained models keras tensorflow scikit learn core ml ios11 Swift4 scikitlearn artificial neural network ANN recurrent neural network RNN convolutional neural network CNN ocr character recognition face detection ios 11 swift 4 coreml vision deep learning machine learning neural networks python anaconda trained models keras tensorflow scikit learn core ml ios11 Swift4 scikitlearn artificial neural network ANN recurrent neural network RNN convolutional neural network CNN ocr character recognition face detection ios 11 swift 4 coreml vision deep learning machine learning neural networks python anaconda trained models keras tensorflow scikit learn core ml ios11 Swift4 scikitlearn artificial neural network ANN recurrent neural network RNN convolutional neural network CNN ocr character recognition face detection ios 11 swift 4 coreml vision deep learning machine learning neural networks python anaconda trained models keras tensorflow scikit learn core ml ios11 Swift4 scikitlearn artificial neural network ANN recurrent neural network RNN convolutional neural network CNN ocr character recognition face detection 

Who is the target audience?

  • People with a basic foundation in iOS programming who would like to discover Machine Learning, a branch of Artificial Intelligence
  • People who want to pursue a career combining app development and Machine Learning to become a hybrid iOS developer and ML expert
  • Developers who would like to apply their Machine Learning skills by creating practical mobile apps
  • Entrepreneurs who want to leverage the exponential technology of Machine Learning to create added value to their business could also take this course. However, this course does assume that you are familiar with basic programming concepts such as object oriented programming, variables, methods, classes, and conditional statements
Basic knowledge
  • Basic understanding of programming
  • Have access to a MAC computer or MACinCloud website
What you will learn
  • Build smart iOS 11 & Swift 4 apps using Machine Learning
  • Use trained ML models in your apps
  • Convert ML models to iOS ready models
  • Create your own ML models
  • Apply Object Prediction on pictures, videos, speech and text
  • Discover when and how to apply a smart sense to your apps
Curriculum
Lectures quantity: 93
Common duration: 07:18:59
Session #1 Getting started
  • About Your Instructor and Course Overview  
  • About Machine Learning  
  • Activity: Playing with Machine Learning Style Transfer  
Session #2 Optional - iOS Fundamentals
  • About this section - start iOS  

    Here is an overview of this new section.

  • Download and install xcode for iOS 11  

    In this lecture, you will learn how to download and install xcode for iOS 11.

  • Get the iOS developer license  

    In this lecture, you will learn how to get the Apple developer license for iOS.

  • How to use a MAC on Windows PC or Linux  

    In this lecture, you will learn how to use a MAC computer on Windows PC and on Linux.

  • How to install iOS 11 on your iPhone or iPad  

    In this lecture, you will learn how to install the iOS 11 on your iPhone or iPad.

  • Use the Xcode interface  

    In this lecture, you will learn how to use Xcode interface.

  • Xcode configuration files  

    In this lecture, you will learn how to work with xcode configuration files.

Session #3 Optional - Machine Learning Concepts
  • About this section - intro to ML  

    Here is an overview of this new section.

  • What is an Artificial Neuron - Neural Network  

    In this lecture, you will get a quick and simple explanation of what an artificial neuron is and how they form a neural network.

  • Parts of an Artificial Neural Network  

    In this lecture, you will get a quick and simple explanation of how an Artificial Neural Network functions.

  • Explanation - Convolutional Neural Network  

    In this lecture, you will get a quick and simple explanation of what how a Convolution Neural Network functions.

  • Recurrent Neural Networks basics RNNs  

    In this lecture, you will get a quick and simple explanation of what parts make up a Recurrent Neural Network.

Session #4 iOS Machine Learning With Photos
  • About this section - coreML with Photos  

    Here is an overview of this new section.

    Please download the Cheat Sheet PDF file.

  • Demo of project using coreML on photos  

    In this lecture, we will give a quick demonstration of what we're trying to achieve in this section.

  • About ML model and Neural Networks  

    In this lecture, you will learn about machine learning models and neural networks.

  • Project: Create the xcode project  

    In this lecture, you will learn how to create an xcode project that uses Swift.

  • Project: How to add ML models to xcode projects  

    In this lecture, you will learn how to add ML models into XCode projects.

  • Project: How to get pre-made ML models for iOS  

    In this lecture, you will learn how to get pre-made, iOS ready, machine learning models.

  • Project: How to use ML models with images (part 1)  

    In this lecture, you will learn how to use ML models that take images as input (part 1 of 2).

  • Project: How to use ML models with images (part 2)  

    In this lecture, you will learn how to use ML models that take images as input (part 2 of 2).

  • Project: Programming the VN request callback method  

    In this lecture, you will learn how to program a Vision Request callback method to process the trained model prediction results.

    Note: Vision framework always returns the best prediction as the first element of the results array.

  • Testing different ML models  

    In this lecture, you will get to test different ML models.

  • Exercise: Models with Images input  

    Here is an exercise to make sure you've grasped what we've learned so far.

  • Solution: Models with Images input  

    Solution of the previous lecture's exercise.

  • Summary: coreML Vision with Photos  

    Here is a summary of what we've learned so far, and how to go in depth

Session #5 coreML All about custom models
  • About this section - model conversion  

    Here is an overview of this new section.

  • Project: Finding custom ML models  

    In this lecture, you will learn how to find custom ML models that are not served by Apple.

  • Project: Converting ML models get Anaconda IDE  

    In this lecture, you will learn how to get the development environment named Anaconda, which is an amazing tool for AI scientists

  • Installing Python libraries for core ML  

    In this lecture, you will learn how to install the python packages (libraries) to work with CoreML.

  • Installing Caffe tools for core ML conversion  

    In this lecture, you will learn how to install Caffee tools to convert Caffe model types to .mlmodel ones.

  • Project: Converting scikit model to core ml mlmodel format  

    In this lecture, you will learn how to convert scikit models to coreML mlmodel format.

Session #6 CoreML with Data Set models
  • Introduction to Working with Data sets  

    Here is an overview of this new section.

  • Project: Create xcode project and add iris model  

    In this lecture, you will learn create a new xcode project and add the custom iris.mlmodel we created in previous lectures.

  • Project: ML dataset project User Interface  

    In this lecture, you will learn how to build the project's User Interface.

  • Project: Pickerview data source methods  

    In this lecture, you will learn how to program the pickerview data source methods.

  • Project: Coding prediction for data sets  

    In this lecture, you will learn how to code model prediction for data sets.

  • Project: Code improvements  

    Here, we'll make some code improvements.

  • Important data set models information  

    We'll go over import informations on data set models.

Session #7 Project: coreML with Video Camera
  • About CoreML with Video Camera  
  • Project: Create xcode project and add VGG16 model  

    In this lecture, you will learn how to create the xcode project and add the fat VGG16 model to our project.

  • Project: Building the user interface  

    Let's build the project's user interface.

  • Project: Video Stream variables setup  

    Let's setup variables to capture the camera video stream.

  • Project: Program camera feed  

    In this lecture, you will learn how to program the camera feed.

  • Project: Capture image from video stream for ML model  

    In this lecture, you will learn how to capture images from the video stream so that we can analyze them with an mlmodel prediction.

  • Project: Programming the ML prediction launch  

    In this lecture, you will learn how to program the ML prediction launch.

  • Project: Processing the ML model output  

    In this lecture, you will learn how to process the ML model results.

  • Testing the live camera feed with VGG model  

    We finally get to test all our hard work:

    Note: R2D2 definitely looks like a trash can and Yoda like a green hot baked potato, don't you think?!

Session #8 END: iOS coreML fundamentals
  • Congratulations  
Session #9 Optional - Going the extra mile
  • Adding converted model metadata  

    In this lecture, you will learn how to add converted model's metadata.

  • Get a PixelBuffer from a UIImage  

    In this lecture, you will learn how to get a pixelbuffer from a UIImage.

  • UIImage PixelBuffer extension (part 1)  

    In this lecture, you will learn how to extend a uiimage to return a pixel buffer (part 1 of 2)

  • UIImage PixelBuffer extension (part 2)  

    In this lecture, you will learn how to extend a uiimage to return a pixel buffer (part 2 of 2)

  • coreML prediction using UIImage PixelBuffer  

    In this lecture, you will learn how to use the UIImage pixel buffer for predictions.

Session #10 Optional - Numerous Model Conversion
  • Caffe - Get a Caffe ML model with weights and labels  

    In this lecture, you will learn how to get a Caffe model, weights and labels.

  • CoreML tools conversion code with Caffe  

    In this lecture, you will learn how to code the conversion of a Caffe model using its trained data, weights, labels, scale and rgb means.

  • Exporting Caffe model to mlmodel format  

    In this lecture, you will learn how to export the caffemodel to mlmodel format.

  • Caffe - Using the Caffe model with iOS  

    In this lecture, you will finally get to see the converted Caffe model used in the iOS app. Isn't it amazing?

  • Keras - Load Save Keras models and convert to mlmodel  

    In this lecture, you will learn how to find Keras models, open them in a Python editor, and run the code.

    You will also learn how to save and retrieve the data models and finally get to convert them to .MLMODEL format to be able to use them in iOS apps.

  • Vision Image Request parameter options  

    In this lecture, you will learn how to use different type of inputs for the VNImageRequestHandler.

Session #11 Advanced Vision Techniques: Face Detection
  • Introduction to advanced ML with Vision  

    Important: Some projects files won't include resources files like puppy.jpg and Inceptionv3.mlmodel because of their big size. You'll need to download the ML models yourself on the apple developer website (i left the file reference in the projects)

  • Project: Create the user interface in storyboard  
  • Project: Coding the Photo selection  
  • Project: Coding Face Detection  
  • Activity: Face Detection  
  • Activity Solution: Face Detection  
Session #12 Optional - Advanced Face Features Detection
  • About Advanced Face Feature Recognition  
  • Locate face position and area (part 1 of 2)  
  • Locate face position and area (part 2 of 2)  
  • Code to detect Face features eyes nose lips  
  • face features part 2  
  • face features part 3  
  • face features part 4  
  • Activity - draw all face features in blue  
  • Activity Solution  
Session #13 Advanced Text Detection Techniques
  • About Project: Text Detection  
  • Project: text recog part 1  
  • Project: text recog part 2  
  • Project: text recog part 3  

    Important: the attached project file named "TextDetectionCompletedV3.zip" also shows you how to capture individual characters:

    guard let chars = box.characterBoxes else {

              print("no characters found")

              return

            }

            for char in chars

            {

              let view = Helper.createOutlineRect(withColor: UIColor.green)

              view.frame = Helper.transformRect(fromRect: char.boundingBox, toViewRect: self.textImageView)

              self.textImageView.image = self.textImageView.image

              self.textImageView.addSubview(view)

            }

  • Activity: Text Recognition  
  • Solution: Text Recognition  
Session #14 Object Tracking (advanced)
  • Demo: Object Tracking Project  
  • Create Object Tracking Project and UI  
  • Program Video Camera Stream  
  • Coding the camera stream launch  
  • Capturing Data and Perform Tracking Request  
  • Coding the tracking request completion handler  
  • Program the object tracking launch  
  • Final Modifications  
  • Final Project Demo  
Session #15 BONUS
  • Ever growing list of Core ML models  
reviews (0)
Average rating
0
0 voices
Detailed rating
5 stars
0%
4 stars
0%
3 stars
0%
2 stars
0%
1 stars
0%