HOME BOOKS VIDEO COURSES
NEWSLETTER CONTACT
Apple Intelligence for Masterminds
How to Create Intelligent Applications for iPhones, iPads and Macs
1st Edition
January 2026
ISBN: 978-1-7779782-8-0
Buy Now
Figures
Book retailers often compress images in ebooks to reduce file size, which can lower visual quality and make some illustrations difficult to read. If this is affecting your reading experience, you can download all the images included in Apple Intelligence for Masterminds, or open any individual image you want to view from the list below.
Download Figures
47.1 MBytes
Chapter 1 — App Development
Figure 1-1: Apple Intelligence options
Figure 1-2: Apple Intelligence downloading resources
Figure 1-3: Xcode in the App Store
Figure 1-4: Xcode's welcome screen
Figure 1-5: Playground option
Figure 1-6: Playground templates
Figure 1-7: Playground's interface
Figure 1-8: Playground's running mode
Figure 1-9: Results
Figure 1-10: Quick Look icon
Figure 1-11: Project templates
Figure 1-12: Project configuration window
Figure 1-13: Xcode’s interface
Chapter 2 — Apple Intelligence
Figure 2-1: Neuron
Figure 2-2: Neural Network
Figure 2-3: Neural Pattern
Figure 2-4: Interconnected Neural Patterns
Figure 2-5: Perceptron
Figure 2-6: Weighted sum
Figure 2-7: Activation
Figure 2-8: Perceptron Values
Figure 2-9: Calculating the perceptron's activation value
Figure 2-10: Multilayer Perceptron
Figure 2-11: Calculating the activation value of each neuron in a layer
Figure 2-12: Artificial Neural Network
Figure 2-13: Artificial Neural Network designed to identify images of cats and dogs
Figure 2-14: Integrated tools
Figure 2-15: Apple Intelligence frameworks
Figure 2-16: Machine Learning frameworks
Chapter 3 — Xcode
Figure 3-1: Code completion
Figure 3-2: Completion of multiple lines of code
Figure 3-3: Completion of a function
Figure 3-4: Text completion
Figure 3-5: Display Code Prediction option
Figure 3-6: Coding Assistant Setup
Figure 3-7: Signing in to a paid ChatGPT account
Figure 3-8: Coding Assistant panel
Figure 3-9: Coding Assistant request
Figure 3-10: Revert button
Figure 3-11: Coding Assistant following a conversation
Figure 3-12: Choosing symbols for reference
Figure 3-13: Coding Assistant working on a specific file
Figure 3-14: Coding Tools option
Figure 3-15: Coding Tools window
Figure 3-16: Request performed from the coding tool
Figure 3-17: List of conversations
Figure 3-18: Modification history
Figure 3-19: Assistant responding questions
Figure 3-20: Coding Assistant configuration
Figure 3-21: Manually applying changes
Figure 3-22: Attachments button
Figure 3-23: Interface generated by the assistant from a mockup
Figure 3-24: Error message
Figure 3-25: Error fixed by the Coding Assistant
Figure 3-26: Adding a model
Figure 3-27: Adding an external model
Figure 3-28: Anthropic provider added to the list
Figure 3-29: List of models offered by the provider
Figure 3-30: Selecting the model
Figure 3-31: Ollama's download page
Figure 3-32: Ollama's menu
Figure 3-33: Ollama's interface
Figure 3-34: Model options
Figure 3-35: Searching for a model
Figure 3-36: Downloading the selected model
Figure 3-37: Adding a local model to Xcode
Figure 3-38: List of local models
Chapter 4 — Integrated Tools
Figure 4-1: Image Playground interface
Figure 4-2: Generating images with Image Playground
Figure 4-3: Generating multiple images
Figure 4-4: Genmoji interface
Figure 4-5: Attributed text
Figure 4-6: Using Genmojis
Figure 4-7: Application to store Genmojis
Figure 4-8: Using Genmojis in a text field
Figure 4-9: Application to store Genmojis in files
Figure 4-10: Writing Tools
Figure 4-11: Writing Tools disabled for the text field
Figure 4-12: Custom button to open Writing Tools
Figure 4-13: Writing Tools editing only parts of the text
Chapter 5 — Foundation Models
Figure 5-1: The model's response
Figure 5-2: Chat box
Figure 5-3: Chat with complex prompts
Figure 5-4: Model with a personality
Figure 5-5: Same response to the same initial prompt
Figure 5-6: Temperature levels
Figure 5-7: Model responding with integers
Figure 5-8: Guided response
Figure 5-9: Structured responses
Figure 5-10: Using predefined prompts
Figure 5-11: Using a tool to get tourist attractions
Figure 5-12: Using external APIs to get the information we need
Figure 5-13: Option to edit the scheme
Figure 5-14: Foundation model availability settings
Figure 5-15: Availability error
Figure 5-16: Guardrail error
Figure 5-17: Permissive guardrails
Figure 5-18: Limit exceeded error
Figure 5-19: Having multiple conversations
Figure 5-20: Model tagging content
Figure 5-21: Toolkit's folder
Figure 5-22: Terminal app
Figure 5-23: Isolated environments
Figure 5-24: Downloading Miniconda
Figure 5-25: Conda version
Figure 5-26: Working within an environment
Figure 5-27: Getting the folder's path from Finder
Figure 5-28: Navigating to the toolkit folder
Figure 5-29: Sample files
Figure 5-30: Training the adapter
Figure 5-31: Adapter file
Figure 5-32: Adding the adapter file to our project
Figure 5-33: Model adapted to be passionate about the 80s
Chapter 6 — Text Models
Figure 6-1: Detecting English
Figure 6-2: Detecting any language
Figure 6-3: Level of probability
Figure 6-4: Detecting only two languages
Figure 6-5: Counting words
Figure 6-6: List of tokens
Figure 6-7: Extracting the root form of words
Figure 6-8: Displaying the token's type
Figure 6-9: Displaying the lexical class of tokens
Figure 6-10: Displaying names and locations
Figure 6-11: Displaying the confidence
Figure 6-12: Displaying the mood
Figure 6-13: Embeddings
Figure 6-14: Embedding representation in a three-dimensional space
Figure 6-15: Embedding vector
Figure 6-16: Distance between different words
Figure 6-17: Related words
Figure 6-18: Related sentences
Figure 6-19: Translation requirements
Figure 6-20: Translation interface
Figure 6-21: Using Replace with Translation button
Figure 6-22: Instant translation
Figure 6-23: Manually performing a translation
Figure 6-24: Translating always from English to French
Figure 6-25: Selecting languages
Figure 6-26: Automatic language selection
Figure 6-27: Selecting all supported languages
Figure 6-28: Multiple translations at once
Figure 6-29: Asynchronous translation
Chapter 7 — Vision Framework
Figure 7-1: Image categories
Figure 7-2: Categories of multiple images
Figure 7-3: Searching by category
Figure 7-4: Area of interest
Figure 7-5: Heat map applied to the image
Figure 7-6: Relevant objects
Figure 7-7: Aesthetic scores
Figure 7-8: Barcode reader
Figure 7-9: Barcode types
Figure 7-10: Text recognition
Figure 7-11: Recognition and translation
Figure 7-12: Reading a document
Figure 7-13: Reading parts of the text
Figure 7-14: Showing key information to the user
Figure 7-15: Lists
Figure 7-16: Tables
Figure 7-17: Barcodes
Figure 7-18: Face area
Figure 7-19: Face angles
Figure 7-20: Face quality
Figure 7-21: Facial features
Figure 7-22: Human bodies
Figure 7-23: Body joints
Figure 7-24: Body gestures
Figure 7-25: Hands joints
Figure 7-26: Joints identifiers
Figure 7-27: Number gestures
Figure 7-28: Gaussian blur
Figure 7-29: Barcode generator
Figure 7-30: Mask
Figure 7-31: New background
Chapter 8 — Audio Models
Figure 8-1: Speech transcriber presets
Figure 8-2: Dictation transcriber presets
Figure 8-3: File transcription
Figure 8-4: Project Capabilities
Figure 8-5: Adding the microphone
Figure 8-6: Providing the reason to access the microphone
Figure 8-7: Transcribing a dictation
Figure 8-8: Translating a dictation
Figure 8-9: Voice selection
Figure 8-10: Additional voices
Figure 8-11: Premium voices
Figure 8-12: Audio analysis
Figure 8-13: Audio timing
Chapter 9 — Siri
Figure 9-1: Using App Intents
Figure 9-2: Creating a shortcut from the Shortcuts App
Figure 9-3: Using a shortcut
Figure 9-4: App Shortcut Previews option
Figure 9-5: Testing prompts for Siri
Figure 9-6: Adding key to info.plist
Figure 9-7: Adding the INAlternativeAppNames key
Figure 9-8: Adding the alternative names
Figure 9-9: Siri showing the response on the screen
Figure 9-10: Different responses for different inputs
Figure 9-11: Options in Spotlight
Figure 9-12: Parameter dialog
Figure 9-13: Multiple dialogs
Figure 9-14: Disambiguation
Figure 9-15: Finding a movie
Figure 9-16: Intent error
Figure 9-17: Using an App Entity to pick a movie
Figure 9-18: Asking Siri for a movie
Figure 9-19: Snippet view
Figure 9-20: Interactive snippet
Figure 9-21: Confirmation snippet
Figure 9-22: Siri Tips
Chapter 10 — Additional Models
Figure 10-1: Create ML option
Figure 10-2: Create ML app
Figure 10-3: Create ML templates
Figure 10-4: Create ML interface
Figure 10-5: Dataset for image classification
Figure 10-6: Training data
Figure 10-7: Testing data
Figure 10-8: Feature Extractor
Figure 10-9: Iterations
Figure 10-10: Data augmentation
Figure 10-11: Data Augmentation options
Figure 10-12: Feature extraction
Figure 10-13: Training progress
Figure 10-14: Testing results
Figure 10-15: Exploring the results
Figure 10-16: Previews
Figure 10-17: Input and Output
Figure 10-18: Model file
Figure 10-19: Adding a model to the project
Figure 10-20: Model in Xcode
Figure 10-21: Interface to test our model
Figure 10-22: Preview images in the Asset Catalog
Figure 10-23: MNIST dataset
Figure 10-24: MNIST model prediction
Figure 10-25: Logging in to the API Platform
Figure 10-26: API Documentation
Figure 10-27: Account settings
Figure 10-28: OpenAI billing system
Figure 10-29: API Keys
Figure 10-30: Enabling connections
Figure 10-31: Interacting with OpenAI model
Figure 10-32: Creating a Worker
Figure 10-33: Selecting a template
Figure 10-34: Defining the Worker's name and URL
Figure 10-35: Accessing the Worker
Figure 10-36: Edit Code button
Figure 10-37: Folder to store Workers
Figure 10-38: Navigating to the workers folder in Terminal
Figure 10-39: Worker options
Figure 10-40: Worker's files and folders
Figure 10-41: Variables and Secrets
Figure 10-42: Creating a secret key
Figure 10-43: OpenAI response
Figure 10-44: Chatting with the model through the Worker
Figure 10-45: JSON response
Figure 10-46: AI Gateway
Figure 10-47: Gateway list
Figure 10-48: Usage examples
Chapter 11 — Neural Networks
Figure 11-1: Perceptrons connectivity
Figure 11-2: Neural Network Layers
Figure 11-3: Network Training Process
Figure 11-4: Simple network
Figure 11-5: Calculating the activation value of the hidden neuron
Figure 11-6: Calculating the activation value of output neuron
Figure 11-7: Initial parameters
Figure 11-8: Calculating the weighted sum for the hidden neuron
Figure 11-9: Activation functions
Figure 11-10: Sigmoid activation function
Figure 11-11: Applying the Sigmoid function to our network
Figure 11-12: Calculating the weighted sum for the output neuron
Figure 11-13: Full forward pass
Figure 11-14: Network output
Figure 11-15: Mean Error
Figure 11-16: Mean Squared Error
Figure 11-17: Mean Squared Error formula
Figure 11-18: Cross-Entropy Loss formula
Figure 11-19: Cross-Entropy errors
Figure 11-20: Cross-Entropy errors
Figure 11-21: Network's error
Figure 11-22: Rate of change
Figure 11-23: Constant Rule
Figure 11-24: Power Rule
Figure 11-25: Constant Multiple Rule
Figure 11-26: Applying derivative rules
Figure 11-27: Sum Rule
Figure 11-28: Difference Rule
Figure 11-29: Product Rule
Figure 11-30: Quotient Rule
Figure 11-31: Differentiating nested functions
Figure 11-32: Chain Rule
Figure 11-33: Chain of variables
Figure 11-34: Chain Rule to measure water flow
Figure 11-35: Rate of change of Y with respect to W
Figure 11-36: Variables in a neural network
Figure 11-37: Rate of change of C with respect to W2
Figure 11-38: Rate of change of C with respect to ŷ
Figure 11-39: Rate of change of ŷ with respect to W2
Figure 11-40: Rate of change of C with respect to W2
Figure 11-41: Rate of change of C with respect to B2
Figure 11-42: Rate of change of C with respect to W1
Figure 11-43: Validating the chain
Figure 11-44: Rate of change of ŷ with respect to A1
Figure 11-45: Differentiating the Sigmoid function
Figure 11-46: Rate of change of Z1 with respect to W1
Figure 11-47: Derivative of the error function with respect to W1
Figure 11-48: Rate of change of C with respect to B1
Figure 11-49: Rate of change of Z1 with respect to B1
Figure 11-50: Derivative of the error function with respect to B1
Figure 11-51: Gradient descent
Figure 11-52: Gradient descent
Figure 11-53: Issues with gradient descent
Figure 11-54: Output after one round of optimization
Figure 11-55: Network training
Figure 11-56: Package Dependencies
Figure 11-57: Adding a package
Figure 11-58: Adding frameworks to the target
Figure 11-59: Installing Metal Toolchain
Figure 11-60: Tensors
Figure 11-61: Network training with MLX
Figure 11-62: Iris dataset
Figure 11-63: Network's accuracy
Select Country
Paperback
$ 29.95 BUY NOW
Kindle
$ 9.99 BUY NOW
Apple Books
$ 9.99 BUY NOW
Google Books
$ 9.99 BUY NOW
Information
1st Edition
January 2026
ISBN: 978-1-7779782-8-0