Scott Klemmer 02 November 2004 Intelligent UIs Scott Klemmer 02 November 2004
The Direct Manipulation Ideology Display as much information as possible Predictable Rapid, reversable interactions User initiates all actions 02 November 2004 Intelligent UIs
The goal: high information density 02 November 2004 Intelligent UIs
Command Line: Low density and indirect manipulation 02 November 2004 Intelligent UIs
guis have improved density and more direct manipulation… 02 November 2004 Intelligent UIs
…but still have a ways to go 02 November 2004 Intelligent UIs
Ben Shneiderman on design methods “30 years of planning work in AI is essentially down the tubes because of lack of attention to the user interface. The designers deliver a system and the first thing that the users say is, ‘This is great but what we really want to do is change these parameters.’ The designers say, ‘Well, you know, we didn’t put that in the interface.’ They just haven’t thought adequately about the interface, nor done testing early enough.” 02 November 2004 Intelligent UIs
The Intelligent Interfaces Ideology Agents know habits, preferences, interests Mixed initiative: computer is sometimes proactive prompt-based telephone interfaces are an example of complete computer initiative 02 November 2004 Intelligent UIs
Some recent successes Spam Filtering Toyota Prius braking system 02 November 2004 Intelligent UIs
How Spam Filtering Works Uses a Bayesian network Begin with a set of ham (good) and spam messages Look at tokens (email addresses, words) and their relative frequencies in ham and spam e.g., “mortgage” occurs in 400 of 3,000 spam mails and 5 out of 300 legitimate emails. Its spam probability would be 0.8889 ([400/3000] divided by [5/300 + 400/3000]). 02 November 2004 Intelligent UIs
Understanding Intelligent UIs q “Why was this message classified as spam?” 02 November 2004 Intelligent UIs
02 November 2004 Intelligent UIs
02 November 2004 Intelligent UIs
Collaborative Filtering aka recommender systems Introduced in 1992, roughly simultaneously by… David Goldberg, Xerox parc (email) Joe Konstan, Berkeley ->umn (NetNews) …and explored soon after by many, including Pattie Maes, mit media lab (music) 02 November 2004 Intelligent UIs
Traditional DM v. Collaborative Filtering 02 November 2004 Intelligent UIs
How do they work? An Example Algorithm Yezdezard Lashkari, Feature Guided Automated Collaborative Filtering, Masters Thesis, MIT Media Laboratory, 1995. Webhound Firefly 02 November 2004 Intelligent UIs
All automated collaborative filtering algorithms use the following steps to make a recommendation to a user: 02 November 2004 Intelligent UIs
Webhound, Lashkari, 1995 02 November 2004 Intelligent UIs
Webhound, Lashkari, 1995 02 November 2004 Intelligent UIs
Webhound, Lashkari, 1995 02 November 2004 Intelligent UIs
Webhound, Lashkari, 1995 02 November 2004 Intelligent UIs
Webhound, Lashkari, 1995 02 November 2004 Intelligent UIs
Webhound, Lashkari, 1995 02 November 2004 Intelligent UIs
Attentional Interfaces Everywhere Messaging (MIT Media Lab) Scott Hudson (CMU) Eric Horvitz (MSR) 02 November 2004 Intelligent UIs
Everywhere Messaging C. Schmandt, N. Marmasse, S. Marti, N. Sawhney, S. Wheeler, IBM Systems Journal, 2000 Several systems Clues: Finds time-critical emails Active Messenger: Delivers these to one of many devices Nomadic Radio: Wearable audio comMotion: Location-aware 02 November 2004 Intelligent UIs
Clues 02 November 2004 Intelligent UIs
Active Messenger 02 November 2004 Intelligent UIs
Nomadic Radio 02 November 2004 Intelligent UIs
comMotion 02 November 2004 Intelligent UIs