A computer vision application performs image classification directly in the browser without any backend calls by leveraging the device's Neural Processing Unit (NPU).
On-device AI meets user demands for performance, privacy, and offline access while satisfying developer needs for a unified codebase and helpful abstractions.
The emerging WebNN standard provides a model-agnostic, unified abstraction for near-native AI execution in the browser, designed around practical use cases.
WebNN can access all available hardware, with the NPU offering a power-efficient alternative to the GPU for sustained AI workloads on mobile devices.
To experiment with the emerging WebNN standard, developers must use canary browser versions and enable specific flags, but its low-level API can be complex.
Frameworks like ONNX Runtime Web and Transformers.js provide higher-level, task-based abstractions over WebNN, making it easier for app developers to build AI features.
Focus on user experience by providing fallbacks and progress indicators, and look ahead to upcoming built-in browser APIs like the Prompt API that abstract away model management.
The demo applications are built as offline-ready Progressive Web Apps and use Web Workers to run intensive AI computations without freezing the main UI thread.
32:27Christian Liebel
30:36Christian Liebel
33:51Thomas Steiner
27:23Nico Martin
25:47Nathaniel Okenwa
35:16Ankit Patel
22:07Ankit Patel
54:49Ron Dagdag
Jobs that call for the skills explored in this talk.
Speech Processing Solutions
Vienna, Austria
Conrad Electronic SE
RE-INvent Retail GmbH