1 / 18

Intelligent and Adaptive Interfaces

Intelligent and Adaptive Interfaces. Julia Schwarz April 25, 2013. Definition. An intelligent or adaptive interface is an interface that changes according to the current user and/or his/her actions. Two Kinds…. User agents : ‘Little Helper’ that acts on user’s behalf.

adonis
Télécharger la présentation

Intelligent and Adaptive Interfaces

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Intelligent and Adaptive Interfaces Julia Schwarz April 25, 2013

  2. Definition An intelligent or adaptive interface is an interface that changes according to the current user and/or his/her actions.

  3. Two Kinds… User agents: ‘Little Helper’ that acts on user’s behalf. Adaptive interface: the UI changes based on context or user actions.

  4. Outline User Agents Adaptive Interfaces Responsive Interface Libraries (focus: Bootstrap) Machine Learning Libraries (focus: Weka)

  5. ‘Little Helper’ that acts on user’s behalf User Agents

  6. Examples

  7. How Do They Work? • Beyesian Networks: Infer desired action based on observed data and previous user actions (Clippy, Siri). • Use Hidden Markov Models or other probabilistic graphical models usually. • Collaborative Filtering: Find people like you and see what they do (Netflix, Amazon). • Unsupervised Learning: K-Means, Hierarchical Clustering

  8. Tools for User Agents • Found no “UI toolkits” but plenty of libraries • Bayesian Inference: • Infer.NET (C#/F# bindings, ‘probabilistic programming’) • HMM Toolbox for Matlab • GHMM (HMM for C) • Supervised and Unsupervised Learning: • Weka • Matlab Statistics Toolbox • LibSVM: multi-language SVM library • scikit-learn: python (builds on scipy, numpy)

  9. In Depth: Weka • Popular among HCI community • Provides GUI for: • Building & evaluating models • Visualizing data distribution • Selecting optimal features • Basic data manipulation • Warning: you are playing with fire! • Demo!

  10. Aside: Why Did Clippy Fail?

  11. The UI changes based on context or user actions. Adaptive Interfaces

  12. Examples • Toolbars/widgets that autohide • Excel auto-formatting & auto completion • Excel: pull down to extend function • Split menus • Auto format for paste

  13. Examples, cont’d • Adaptive Menus (e.g. more…) • Autoformatting • Self-revealing toolbars • Automatic creation of files/folders e.g. My Music, My Documents • AI failures causes less control, not more thank you to http://www.zuschlogin.com/?p=15

  14. Responsive Design

  15. Is Your Design Responsive? http://mattkersley.com/responsive/

  16. Responsive Design Examples Good: • http://thegreatdiscontent.com/ • http://mattkersley.com/ • http://www.bostonglobe.com/ Bad: • http://cnn.com • http://nytimes.com Fun/Interesting: • http://webdesign.maratz.com/lab/responsivetypography/realtime/

  17. Frameworks for Responsive Design • CSS to make your web pages responsive • Grid-based (lay out your UI in a grid. always) • Bootstrap fluid layout • Foundation • Skeleton • Comparison: http://responsive.vermilion.com/compare.php

  18. Discussion: Are Adaptive Interfaces Good?

More Related