Support real-time ML inference on the CPU
WWDC24
Support real-time ML inference on the CPU Discover how you can use BNNSGraph to accelerate the execution of your machine learning model on the CPU. We will show you how to use BNNSGraph to compile and execute a machine learning model on the CPU and share how it provides real-time guarantees such as no runtime memory allocation and... WWDC24
Get started with Writing Tools
WWDC24
Get started with Writing Tools Learn how Writing Tools help users proofread, rewrite, and transform text in your app. Get the details on how Writing Tools interact with your app so users can refine what they have written in any text view. Understand how text is retrieved and processed, and how to support Writing Tools in... WWDC24
What’s new in Create ML
WWDC24
What’s new in Create ML Explore updates to Create ML, including interactive data source previews and a new template for building object tracking models for visionOS apps. We'll also cover important framework improvements, including new time-series forecasting and classification APIs. WWDC24
Deploy machine learning and AI models on-device with Core ML
WWDC24
Deploy machine learning and AI models on-device with Core ML Learn new ways to optimize speed and memory performance when you convert and run machine learning and AI models through Core ML. We'll cover new options for model representations, performance insights, execution, and model stitching which can be used together to create compelling and private... WWDC24
Bring your app to Siri
WWDC24
Bring your app to Siri Learn how to use SiriKit and App Intents to expose your app's functionality to Siri and Apple Intelligence. Discover which intents are already available for your use, and how to adopt App Intent domains to integrate actions from your app into the system. Find out what metadata to provide, how to... WWDC24
Accelerate machine learning with Metal
WWDC24
Accelerate machine learning with Metal Learn how to accelerate your machine learning transformer models with new features in Metal Performance Shaders Graph. We'll also cover how to improve your model's compute bandwidth and quality, and visualize it in the all new MPSGraph viewer. WWDC24
Discover Swift enhancements in the Vision framework
WWDC24
Discover Swift enhancements in the Vision framework The Vision Framework API has been redesigned to leverage modern Swift features like concurrency, making it easier and faster to integrate a wide array of Vision algorithms into your app. We'll tour the updated API and share sample code, along with best practices, to help you get the benefits of... WWDC24
Bring your machine learning and AI models to Apple silicon
WWDC24
Bring your machine learning and AI models to Apple silicon Learn how to optimize your machine learning and AI models to leverage the power of Apple silicon. Review model conversion workflows to prepare your models for on-device deployment. Understand model compression techniques that are compatible with Apple silicon, and at what stages in your model... WWDC24
Support semantic search with Core Spotlight
WWDC24
Support semantic search with Core Spotlight Learn how to provide semantic search results in your app using Core Spotlight. Understand how to make your app's content available in the user's private, on-device index so people can search for items using natural language. We'll also share how to optimize your app's performance by scheduling... WWDC24
Keep colors consistent across captures
WWDC24
Keep colors consistent across captures Meet the Constant Color API and find out how it can help people use your app to determine precise colors. You'll learn how to adopt the API, explore its scientific and marketing potential, and discover best practices for making the most of the technology. WWDC24
Build a great Lock Screen camera capture experience
WWDC24
Build a great Lock Screen camera capture experience Find out how the LockedCameraCapture API can help you bring your capture application's most useful information directly to the Lock Screen. Examine the API's features and functionality, learn how to get started creating a capture extension, and find out how that extension behaves when the device... WWDC24
Use HDR for dynamic image experiences in your app
WWDC24
Use HDR for dynamic image experiences in your app Discover how to read and write HDR images and process HDR content in your app. Explore the new supported HDR image formats and advanced methods for displaying HDR images. Find out how HDR content can coexist with your user interface — and what to watch out for when adding HDR image support to... WWDC24
Train your machine learning and AI models on Apple GPUs
WWDC24
Train your machine learning and AI models on Apple GPUs Learn how to train your models on Apple Silicon with Metal for PyTorch, JAX and TensorFlow. Take advantage of new attention operations and quantization support for improved transformer model performance on your devices. WWDC24
Introducing enterprise APIs for visionOS
WWDC24
Introducing enterprise APIs for visionOS Find out how you can use new enterprise APIs for visionOS to create spatial experiences that enhance employee and customer productivity on Apple Vision Pro. WWDC24
Design App Intents for system experiences
WWDC24
Design App Intents for system experiences App Intents power system experiences in controls, Spotlight, Siri, and more. Find out how to identify the functionality that's best for App Intents, and how to use parameters to make these intents flexible. Learn how to use App Intents to allow people to take action outside your app, and see... WWDC24
Explore object tracking for visionOS
WWDC24
Explore object tracking for visionOS Find out how you can use object tracking to turn real-world objects into virtual anchors in your visionOS app. Learn how you can build spatial experiences with object tracking from start to finish. Find out how to create a reference object using machine learning in Create ML and attach content... WWDC24
Meet the Translation API
WWDC24
Meet the Translation API Discover how you can translate text across different languages in your app using the new Translation framework. We'll show you how to quickly display translations in the system UI, and how to translate larger batches of text for your app's UI. WWDC24
Bring your app’s core features to users with App Intents
WWDC24
Bring your app’s core features to users with App Intents Learn the principles of the App Intents framework, like intents, entities, and queries, and how you can harness them to expose your app's most important functionality right where people need it most. Find out how to build deep integration between your app and the many system features built on top... WWDC24
What’s new in App Intents
WWDC24
What’s new in App Intents Learn about improvements and all-new features with App Intents, and discover how this framework can help you expose your app's functionality to Siri, Spotlight, Shortcuts, and more. We'll show you how to make your entities more meaningful to the platform with the Transferable API, File... WWDC24
Explore machine learning on Apple platforms
WWDC24
Explore machine learning on Apple platforms Get started with an overview of machine learning frameworks on Apple platforms. Whether you're implementing your first ML model, or an ML expert, we'll offer guidance to help you select the right framework for your app's needs. WWDC24
What’s new in DockKit
WWDC24
What’s new in DockKit Discover how intelligent tracking in DockKit allows for smoother transitions between subjects. We will cover what intelligent tracking is, how it uses an ML model to select and track subjects, and how you can use it in your app. WWDC24
What’s new in VisionKit
WWDC23
What’s new in VisionKit Discover how VisionKit can help people quickly lift subjects from images in your app and learn more about the content of an image with Visual Look Up. We'll also take a tour of the latest updates to VisionKit for Live Text interaction, data scanning, and expanded support for macOS apps.
For more... WWDC23
Lift subjects from images in your app
WWDC23
Lift subjects from images in your app Discover how you can easily pull the subject of an image from its background in your apps. Learn how to lift the primary subject or to access the subject at a given point with VisionKit. We'll also share how you can lift subjects using Vision and combine that with lower-level frameworks like Core... WWDC23
Detect animal poses in Vision
WWDC23
Detect animal poses in Vision Go beyond detecting cats and dogs in images. We'll show you how to use Vision to detect the individual joints and poses of these animals as well — all in real time — and share how you can enable exciting features like animal tracking for a camera app, creative embellishment on an animal photo,... WWDC23
Discover machine learning enhancements in Create ML
WWDC23
Discover machine learning enhancements in Create ML Find out how Create ML can help you do even more with machine learning models. Learn about the latest updates to image understanding and text-based tasks with multilingual BERT embeddings. Discover how easy it is to train models that can understand the content of images using multi-label... WWDC23
Explore 3D body pose and person segmentation in Vision
WWDC23
Explore 3D body pose and person segmentation in Vision Discover how to build person-centric features with Vision. Learn how to detect human body poses and measure individual joint locations in 3D space. We'll also show you how to take advantage of person segmentation APIs to distinguish and segment up to four individuals in an image.
To learn more... WWDC23
Explore Natural Language multilingual models
WWDC23
Explore Natural Language multilingual models Learn how to create custom Natural Language models for text classification and word tagging using multilingual, transformer-based embeddings. We'll show you how to train with less data and support up to 27 different languages across three scripts. Find out how to use these embeddings to fine-tune... WWDC23
Optimize machine learning for Metal apps
WWDC23
Optimize machine learning for Metal apps Discover the latest enhancements to accelerated ML training in Metal. Find out about updates to PyTorch and TensorFlow, and learn about Metal acceleration for JAX. We'll show you how MPS Graph can support faster ML inference when you use both the GPU and Apple Neural Engine, and share how the... WWDC23
Improve Core ML integration with async prediction
WWDC23
Improve Core ML integration with async prediction Learn how to speed up machine learning features in your app with the latest Core ML execution engine improvements and find out how aggressive asset caching can help with inference and faster model loads. We'll show you some of the latest options for async prediction and discuss considerations for... WWDC23
Use Core ML Tools for machine learning model compression
WWDC23
Use Core ML Tools for machine learning model compression Discover how to reduce the footprint of machine learning models in your app with Core ML Tools. Learn how to use techniques like palettization, pruning, and quantization to dramatically reduce model size while still achieving great accuracy. Explore comparisons between compression during the... WWDC23
Integrate with motorized iPhone stands using DockKit
WWDC23
Integrate with motorized iPhone stands using DockKit Discover how you can create incredible photo and video experiences in your camera app when integrating with DockKit-compatible motorized stands. We'll show how your app can automatically track subjects in live video across a 360-degree field of view, take direct control of the stand to customize... WWDC23
Customize on-device speech recognition
WWDC23
Customize on-device speech recognition Find out how you can improve on-device speech recognition in your app by customizing the underlying model with additional vocabulary. We'll share how speech recognition works on device and show you how to boost specific words and phrases for more predictable transcription. Learn how you can... WWDC23
Get to know Create ML Components
WWDC22
Get to know Create ML Components Create ML makes it easy to build custom machine learning models for image classification, object detection, sound classification, hand pose classification, action classification, tabular data regression, and more. And with the Create ML Components framework, you can further customize underlying... WWDC22
Capture machine-readable codes and text with VisionKit
WWDC22
Capture machine-readable codes and text with VisionKit Meet the Data Scanner in VisionKit: This framework combines AVCapture and Vision to enable live capture of machine-readable codes and text through a simple Swift API. We'll show you how to control the types of content your app can capture by specifying barcode symbologies and language selection... WWDC22
What's new in Create ML
WWDC22
What's new in Create ML Discover the latest updates to Create ML. We'll share improvements to Create ML's evaluation tools that can help you understand how your custom models will perform on real-world data. Learn how you can check model performance on each type of image in your test data and identify problems within... WWDC22
Compose advanced models with Create ML Components
WWDC22
Compose advanced models with Create ML Components Take your custom machine learning models to the next level with Create ML Components. We'll show you how to work with temporal data like video or audio and compose models that can count repetitive human actions or provide advanced sound classification. We'll also share best practices on using... WWDC22
Optimize your Core ML usage
WWDC22
Optimize your Core ML usage Learn how Core ML works with the CPU, GPU, and Neural Engine to power on-device, privacy-preserving machine learning experiences for your apps. We'll explore the latest tools for understanding and maximizing the performance of your models. We'll also show you how to generate reports to easily... WWDC22
What's new in Vision
WWDC22
What's new in Vision Learn about the latest updates to Vision APIs that help your apps recognize text, detect faces and face landmarks, and implement optical flow. We'll take you through the capabilities of optical flow for video-based apps, show you how to update your apps with revisions to the machine learning... WWDC22
Explore the machine learning development experience
WWDC22
Explore the machine learning development experience Learn how to bring great machine learning (ML) based experiences to your app. We'll take you through model discovery, conversion, and training and provide tips and best practices for ML. We'll share considerations to take into account as you begin your ML journey, demonstrate techniques for... WWDC22
Accelerate machine learning with Metal
WWDC22
Accelerate machine learning with Metal Discover how you can use Metal to accelerate your PyTorch model training on macOS. We'll take you through updates to TensorFlow training support, explore the latest features and operations of MPS Graph, and share best practices to help you achieve great performance for all your machine learning... WWDC22
Improve Object Detection models in Create ML
Tech Talks
Improve Object Detection models in Create ML When you train custom Core ML models for object detection in Create ML, you can bring image understanding to your app. Discover how transfer learning allows you to build smaller models with less training data. We'll also take you through some of the advanced parameters in Create ML that help you... Tech Talks
Explore and manipulate data in Swift with TabularData
Tech Talks
Explore and manipulate data in Swift with TabularData Discover how you can use the TabularData framework to load, explore, and manipulate unstructured data in Swift — whether you need to pre-process data for a machine learning task or digest data on-the-fly in your app. Learn how this framework can help you handle large datasets, join multiple... Tech Talks
Convert PyTorch models to Core ML
Tech Talks
Convert PyTorch models to Core ML Bring your PyTorch models to Core ML and discover how you can leverage on-device machine learning in your apps.
The PyTorch machine learning framework can help you create and train complex neural networks. After you build these models, you can convert them to Core ML and run them entirely... Tech Talks
The process of inclusive design
WWDC21
The process of inclusive design Discover how you can deliver inclusive apps that can foster amazing experiences for everyone who uses your software. We'll take you through best practices for creating and empowering diverse teams and explore how inclusivity influences every stage of the design and development process. WWDC21
Discoverable design
WWDC21
Discoverable design Discover how you can create interactive, memorable experiences to onboard people into your app. We'll take you through discoverable design practices and learn how you can craft explorable, fun interfaces that help people grasp the possibilities of your app at a glance. We'll also show you how to... WWDC21
Discover built-in sound classification in SoundAnalysis
WWDC21
Discover built-in sound classification in SoundAnalysis Explore how you can use the Sound Analysis framework in your app to detect and classify discrete sounds from any audio source — including live sounds from a microphone or from a video or audio file — and identify precisely in a moment where that sound occurs. Learn how the built-in sound... WWDC21
Detect people, faces, and poses using Vision
WWDC21
Detect people, faces, and poses using Vision Discover the latest updates to the Vision framework to help your apps detect people, faces, and poses. Meet the Person Segmentation API, which helps your app separate people in images from their surroundings, and explore the latest contiguous metrics for tracking pitch, yaw, and the roll of the... WWDC21
Build dynamic iOS apps with the Create ML framework
WWDC21
Build dynamic iOS apps with the Create ML framework Discover how your app can train Core ML models fully on device with the Create ML framework, enabling adaptive and customized app experiences, all while preserving data privacy. We'll explore the types of models that can be created on-the-fly for image-based tasks like Style Transfer and Image... WWDC21
Classify hand poses and actions with Create ML
WWDC21
Classify hand poses and actions with Create ML With Create ML, your app's ability to understand the expressiveness of the human hand has never been easier. Discover how you can build off the support for Hand Pose Detection in Vision and train custom Hand Pose and Hand Action classifiers using the Create ML app and framework. Learn how simple... WWDC21
Extract document data using Vision
WWDC21
Extract document data using Vision Discover how Vision can provide expert image recognition and analysis in your app to extract information from documents, recognize text in multiple languages, and identify barcodes. We'll explore the latest updates to Text Recognition and Barcode Detection, show you how to bring all these tools... WWDC21
Accelerate machine learning with Metal Performance Shaders Graph
WWDC21
Accelerate machine learning with Metal Performance Shaders Graph Metal Performance Shaders Graph is a compute engine that helps you build, compile, and execute customized multidimensional graphs for linear algebra, machine learning, computer vision, and image processing. Discover how MPSGraph can accelerate the popular TensorFlow platform through a Metal... WWDC21
Tune your Core ML models
WWDC21
Tune your Core ML models Bring the power of machine learning directly to your apps with Core ML. Discover how you can take advantage of the CPU, GPU, and Neural Engine to provide maximum performance while remaining on device and protecting privacy. Explore MLShapedArray, which makes it easy to work with multi-dimensional... WWDC21
Use Accelerate to improve performance and incorporate encrypted archives
WWDC21
Use Accelerate to improve performance and incorporate encrypted archives The Accelerate framework helps you make large-scale mathematical computations and image calculations that are optimized for high-performance, low-energy consumption. Explore the latest updates to Accelerate and its Basic Neural Network Subroutines library, including additional layers, activation... WWDC21
Use model deployment and security with Core ML
WWDC20
Use model deployment and security with Core ML Discover how to deploy Core ML models outside of your app binary, giving you greater flexibility and control when bringing machine learning features to your app. And learn how Core ML Model Deployment enables you to deliver revised models to your app without requiring an app update. We'll also... WWDC20
Detect Body and Hand Pose with Vision
WWDC20
Detect Body and Hand Pose with Vision Explore how the Vision framework can help your app detect body and hand poses in photos and video. With pose detection, your app can analyze the poses, movements, and gestures of people to offer new video editing possibilities, or to perform action classification when paired with an action... WWDC20
Build an Action Classifier with Create ML
WWDC20
Build an Action Classifier with Create ML Discover how to build Action Classification models in Create ML. With a custom action classifier, your app can recognize and understand body movements in real-time from videos or through a camera. We'll show you how to use samples to easily train a Core ML model to identify human actions like... WWDC20
Explore the Action & Vision app
WWDC20
Explore the Action & Vision app It's now easy to create an app for fitness or sports coaching that takes advantage of machine learning — and to prove it, we built our own. Learn how we designed the Action & Vision app using Object Detection and Action Classification in Create ML along with the new Body Pose... WWDC20
Explore Computer Vision APIs
WWDC20
Explore Computer Vision APIs Learn how to bring Computer Vision intelligence to your app when you combine the power of Core Image, Vision, and Core ML. Go beyond machine learning alone and gain a deeper understanding of images and video. Discover new APIs in Core Image and Vision to bring Computer Vision to your application... WWDC20
Build Image and Video Style Transfer models in Create ML
WWDC20
Build Image and Video Style Transfer models in Create ML Bring stylized effects to your photos and videos with Style Transfer in Create ML. Discover how you can train models in minutes that make it easy to bring creative visual features to your app. Learn about the training process and the options you have for controlling the results. And we'll explore... WWDC20
Make apps smarter with Natural Language
WWDC20
Make apps smarter with Natural Language Explore how you can leverage the Natural Language framework to better analyze and understand text. Learn how to draw meaning from text using the framework's built-in word and sentence embeddings, and how to create your own custom embeddings for specific needs.
We'll show you how to use samples... WWDC20
Get models on device using Core ML Converters
WWDC20
Get models on device using Core ML Converters With Core ML you can bring incredible machine learning models to your app and run them entirely on-device. And when you use Core ML Converters, you can incorporate almost any trained model from TensorFlow or PyTorch and take full advantage of the GPU, CPU, and Neural Engine. Discover everything... WWDC20
Build customized ML models with the Metal Performance Shaders Graph
WWDC20
Build customized ML models with the Metal Performance Shaders Graph Discover the Metal Performance Shaders (MPS) Graph, which extends Metal's Compute capabilities to multi-dimensional Tensors. MPS Graph builds on the highly tuned library of data parallel primitives that are vital to machine learning and leverages the tremendous power of the GPU. Explore how MPS... WWDC20
Control training in Create ML with Swift
WWDC20
Control training in Create ML with Swift With the Create ML framework you have more power than ever to easily develop models and automate workflows. We'll show you how to explore and interact with your machine learning models while you train them, helping you get a better model quickly. Discover how training control in Create ML can... WWDC20
Introducing the Create ML App
WWDC19
Introducing the Create ML App Bringing the power of Core ML to your app begins with one challenge. How do you create your model? The new Create ML app provides an intuitive workflow for model creation. See how to train, evaluate, test, and preview your models quickly in this easy-to-use tool. Get started with one of the many... WWDC19
Core ML 3 Framework
WWDC19
Core ML 3 Framework Core ML 3 now enables support for advanced model types that were never before available in on-device machine learning. Learn how model personalization brings amazing personalization opportunities to your app. Gain a deeper understanding of strategies for linking models and improvements to Core ML... WWDC19
What's New in Machine Learning
WWDC19
What's New in Machine Learning Core ML 3 has been greatly expanded to enable even more amazing, on-device machine learning capabilities in your app. Learn about the new Create ML app which makes it easy to build Core ML models for many tasks. Get an overview of model personalization; exciting updates in Vision, Natural... WWDC19
Advances in Speech Recognition
WWDC19
Advances in Speech Recognition Speech Recognizer can now be used locally on iOS or macOS devices with no network connection. Learn how you can bring text-to-speech support to your app while maintaining privacy and eliminating the limitations of server-based processing. Speech recognition API has also been enhanced to provide... WWDC19
Training Sound Classification Models in Create ML
WWDC19
Training Sound Classification Models in Create ML Learn how to quickly and easily create Core ML models capable of classifying the sounds heard in audio files and live audio streams. In addition to providing you the ability to train and evaluate these models, the Create ML app allows you to test the model performance in real-time using the... WWDC19
Training Object Detection Models in Create ML
WWDC19
Training Object Detection Models in Create ML Custom Core ML models for Object Detection offer you an opportunity to add some real magic to your app. Learn how the Create ML app in Xcode makes it easy to train and evaluate these models. See how you can test the model performance directly within the app by taking advantage of Continuity... WWDC19
Training Text Classifiers in Create ML
WWDC19
Training Text Classifiers in Create ML Create ML now enables you to create models for Natural Language that are built on state-of-the-art techniques. Learn how these models can be easily trained and tested with the Create ML app. Gain insight into the powerful new options for transfer learning, word embeddings, and text catalogs. WWDC19
Understanding Images in Vision Framework
WWDC19
Understanding Images in Vision Framework Learn all about the many advances in the Vision Framework including effortless image classification, image saliency, determining image similarity, and improvements in facial feature detection, and face capture quality scoring. This packed session will show you how easy it is to bring powerful... WWDC19
Training Recommendation Models in Create ML
WWDC19
Training Recommendation Models in Create ML Recommendation models for Core ML can enable a very personal experience for the customers using your app. They power suggestions for what music to play or what movie to see in the apps you use every day. Learn how you can easily create a custom Recommendation model from all sorts of data sources... WWDC19
Building Activity Classification Models in Create ML
WWDC19
Building Activity Classification Models in Create ML Your iPhone and Apple Watch are loaded with a number of powerful sensors including an accelerometer and gyroscope. Activity Classifiers can be trained on data from these sensors to bring some magic to your app, such as knowing when someone is running or swinging a bat. Learn how the Create ML app... WWDC19
Advances in Natural Language Framework
WWDC19
Advances in Natural Language Framework Natural Language is a framework designed to provide high-performance, on-device APIs for natural language processing tasks across all Apple platforms. Learn about the addition of Sentiment Analysis and Text Catalog support in the framework. Gain a deeper understanding of transfer learning for... WWDC19
Creating Great Apps Using Core ML and ARKit
WWDC19
Creating Great Apps Using Core ML and ARKit Take a journey through the creation of an educational game that brings together Core ML, ARKit, and other app frameworks. Discover opportunities for magical interactions in your app through the power of machine learning. Gain a deeper understanding of approaches to solving challenging computer... WWDC19
Text Recognition in Vision Framework
WWDC19
Text Recognition in Vision Framework Document Camera and Text Recognition features in Vision Framework enable you to extract text data from images. Learn how to leverage this built-in machine learning technology in your app. Gain a deeper understanding of the differences between fast versus accurate processing as well as... WWDC19
Designing Great ML Experiences
WWDC19
Designing Great ML Experiences Machine learning enables new experiences that understand what we say, suggest things that we may love, and allow us to express ourselves in new, rich ways. Machine learning can make existing experiences better by automating mundane tasks and improving the accuracy and speed of interactions. Learn... WWDC19
Metal for Machine Learning
WWDC19
Metal for Machine Learning Metal Performance Shaders (MPS) includes a highly tuned library of data parallel primitives vital to machine learning and leveraging the tremendous power of the GPU. With iOS 13 and macOS Catalina, MPS improves performance, enables more neural networks, and is now even easier to use. Learn more... WWDC19
20:03 
12:24 
11:32 
18:15 
21:49 
25:06 
16:49 
30:09 
10:55 
23:48 
22:49 
34:29 
18:21 
21:18 
9:19 
17:01 
16:31 
26:02 
17:56 
17:33 
16:06 
19:56 
18:38 
13:47 
16:50 
14:38 
14:25 
21:15 
23:21 
25:18 
17:35 
7:52 
25:31 
12:11 
16:46 
13:25 
23:30 
19:48 
17:19 
29:51 
15:48 
23:48 
25:18 
36:34 
32:44 
19:16 
17:58 
16:49 
26:49 
19:12 
29:12 
24:30 
14:22 
24:42 
24:21 
26:06 
36:27 
24:35 
11:48 
41:04 
31:16 
39:35 
18:39 
14:34 
40:38 
14:49 
6:10 
20:11 
15:41 
12:05 
39:50 
10:31 
15:01 
39:19 
29:43 
38:15 
57:45 
41:25