Interacting with a computer requires adopting some metaphor to guide our actions and expectations. Most human-computer interfaces can be classified according to two dominant metaphors: (1) agent and (2) environment. Interactions based on an agent metaphor treat the computer as an intermediary that responds to user requests. In the environment metaphor, a model of the task domain is presented for the user to interact with directly. The term agent has come to refer to the automation of aspects of human-computer interaction (HCI), such as anticipating commands or autonomously performing actions. Norman's 1984 model of HCI is introduced as reference to organize and evaluate research in human-agent interaction (HAI). A wide variety of heterogeneous research involving HAI is shown to reflect automation of one of the stages of action or evaluation within Norman's model. Improvements in HAI are expected to result from a more heterogeneous use of methods that target multiple stages simultaneously.

A number of approaches have been advanced for taking data about a user's likes and dislikes and generating a general profile of the user. These profiles can be used to retrieve documents matching user interests; recommend music, movies, or other similar products; or carry out other tasks in a specialized fashion. This article presents a fundamentally new method for generating user profiles that takes advantage of a large-scale database of demographic data. These data are used to generalize user-specified data along the patterns common across the population, including areas not represented in the user's original data. I describe the method in detail and present its implementation in the LIFESTYLE FINDER agent, an internet-based experiment testing our approach on more than 20,006 users worldwide.

The value of scientific digital-image libraries seldom lies in the pixels of images. For large collections of images, such as those resulting from astronomy sky surveys, the typical useful product is an online database cataloging entries of interest. We focus on the automation of the cataloging effort of a major sky survey and the availability of digital libraries in general. The SKICAT system automates the reduction and analysis of the three terabytes worth of images, expected to contain on the order of 2 billion sky objects. For the primary scientific analysis of these data, it is necessary to detect, measure, and classify every sky object. SKICAT integrates techniques for image processing, classification learning, database management, and visualization. The learning algorithms are trained to classify the detected objects and can classify objects too faint for visual classification with an accuracy level exceeding 90 percent. This accuracy level increases the number of classified objects in the final catalog threefold relative to the best results from digitized photographic sky surveys to date. Hence, learning algorithms played a powerful and enabling role and solved a difficult, scientifically significant problem, enabling the consistent, accurate classification and the ease of access and analysis of an otherwise unfathomable data set.

A significant and growing area of business-computing research is concerned with AI. Knowledge about which journals are the most influential forums for disseminating AI research is important for business school faculty, students, administrators, and librarians. To date, there has been only one study attempting to rank AI journals from a business-computing perspective. It used a subjective methodology, surveying opinions of business faculty about a prespecified list of 30 journals. Here, we report the results of a more objective study. We conducted a citation analysis covering a time period of 5 years to compile 15,600 citations to 1,244 different journals. Based on these data, the journals are ranked in two ways involving the magnitude and the duration of scientific impact each has had in the field of AI.

There are many different possible schemes for converting hand gestures to speech. The choice of scheme depends on the granularity of the speech that you want to produce. Figure 1 identifies a spectrum defined by possible divisions of speech based on the duration of the sound for each granularity. What is interesting is that in general, the coarser the division of speech, the smaller the bandwidth necessary for the user. In contrast, where the granularity of speech is on the order of articulatory musclemovements (i.e. the artificial vocal tract [AVT]) high bandwidth control is necessary for good speech. Devices which implement this model of speech production are like musical instruments which produce speech sounds.

In recent years, NIPS has heard neural networks generate tunes and harmonize chorales. With a large amount of music becoming available in computer readable form, real data can be used to train connectionist models. At the beginning of this workshop, Andreas Weigend focused on architectures to capture structure on multiple time scales.

Mozer, 1991; Bharucha, 1992), the models rarely explain the way in which musical representations are constructed and learned.

This study explores the extent to which a network that learns the temporal relationships within and between the component features of Western tonal music can account for music theoretic and psychological phenomena such as the tonal hierarchy and rhythmic expectancies. Predicted and generated sequences were recorded as the representation of a 153-note waltz melody was learnt by a predictive, recurrent network. The network learned transitions and relations between and within pitch and timing components: accent and duration values interacted in the development of rhythmic and metric structures and, with training, the network developed chordal expectancies in response to the activation of individual tones. Analysis of the hidden unit representation revealed that musical sequences are represented as transitions between states in hidden unit space.

In recent years, NIPS has heard neural networks generate tunes and harmonize chorales. With a large amount of music becoming available in computer readable form, real data can be used to train connectionist models. At the beginning of this workshop, Andreas Weigend focused on architectures to capture structure on multiple time scales.

The first Robotics Exhibition and Competition sponsored by the Association for the Advancement of Artificial Intelligence was held in San Jose, California, on 14-16 July 1992 in conjunction with the Tenth National Conference on AI. This article describes the history behind the competition, the preparations leading to the competition, the threedays during which 12 teams competed in the three events making up the competition, and the prospects for other such competitions in the future.