We propose a new network growing method to detect salient features in input patterns. The new method is based upon a previous network growing model (R. Kamimura and T. Kamimura, 2002) and introduced to overcome some p...
详细信息
We propose a new network growing method to detect salient features in input patterns. The new method is based upon a previous network growing model (R. Kamimura and T. Kamimura, 2002) and introduced to overcome some problems in the previous model. We have so far tried to build a model that can learn input patterns as efficiently as possible. To realize this efficiency, we impose upon networks a constraint that only connections into new competitive units must be updated to absorb as much information as possible from outside. However, one of the problems is that the previous improper feature extraction prevents networks from extracting appropriate features in the later learning stages. To overcome this problem, we relax the condition of the previous model, and we permit networks to update all connections for gradual feature extraction at the expense of computational efficiency. We applied the new method to a simple problem that the previous model cannot solve, and information education data analysis. In both problems, we found that the new method can appropriately extract features from input patterns.
In this paper, we propose a new information theoretic network growing algorithm. The new approach is called greedy information acquisition, because networks try to absorb as much information as possible in every stage...
详细信息
In this paper, we propose a new information theoretic network growing algorithm. The new approach is called greedy information acquisition, because networks try to absorb as much information as possible in every stage of learning. In the first stage, two competitive units compete with each other by maximizing mutual information. In the successive stages, new competitive units are gradually added and information is maximized. Through greedy information maximization, different sets of important features in input patterns can be cumulatively discovered in successive stages. We applied our approach to a language classification problem. Experimental results confirmed that different features in input patterns are gradually discovered.
Professor John Belcher developed a series of short videos with animation and text of selected experiments to properly demonstrate the phenomena of electromagnetism. Such 3D animations are visually compelling, instilli...
详细信息
Professor John Belcher developed a series of short videos with animation and text of selected experiments to properly demonstrate the phenomena of electromagnetism. Such 3D animations are visually compelling, instilling in the student both a sense of wonder about the phenomena and a mental model of why and how it works. The products of these approach includes video clips of demonstrations, 3D animations of these demonstration which display time changing field-lines as a guide to understanding their dynamical effects and Java applets which allow the student to actively construct and animate 2D field lines for varying configurations of sources. These technologies are also implemented to develop animations for Faraday's insights, using video clips.
Many interesting research challenges await the paradigm shift in the relationship between humans and computers. This article highlights those challenges from two distinct perspectives: human-centered;and technology-ce...
详细信息
Many interesting research challenges await the paradigm shift in the relationship between humans and computers. This article highlights those challenges from two distinct perspectives: human-centered;and technology-centered. It also discusses findings from breakout discussions representing these two perspectives.
Intelligent, interactive environments promise to drastically change our everyday lives by connecting computation to the ordinary, human-level events happening in the real world. This paper describes a new model for tr...
详细信息
Intelligent, interactive environments promise to drastically change our everyday lives by connecting computation to the ordinary, human-level events happening in the real world. This paper describes a new model for tracking people in a room through a multi-camera vision system that learns to combine event predictions from multiple video streams. The system is intended to locate and track people in the room, determine their postures, and obtain images of their faces and upper bodies suitable for use during teleconferencing. This paper describes the design and architecture of the vision system and its use in Hal, the most recently constructed interactive space in the authors' Intelligent Room project.
We worked with a team from the Library of Congress (LC) to develop interface design components for LC's American Memory collections of historical multimedia materials. Our prototype illustrates the benefits of pre...
详细信息
Statistical social science databases present many unique data management problems. Among them is the fact that computer-aided use of statistical social science data is subject to serious but preventable errors in data...
详细信息
The use of multivariate information visualization techniques is intrinsically difficult because the multidimensional nature of data cannot be effectively presented and understood on real-world displays, which have lim...
详细信息
暂无评论