In this paper, we propose a new computational method for a network-growing method called greedy network-growing. We have so far introduced a network-growing algorithm called greedy network-growing based upon informati...
详细信息
ISBN:
(纸本)0780386442
In this paper, we propose a new computational method for a network-growing method called greedy network-growing. We have so far introduced a network-growing algorithm called greedy network-growing based upon information theoretic competitive learning. For competitive unit outputs, we have used the inverse of the squares of Euclidean distance between input patterns and connections. The algorithm has extracted very faithful representations of input patterns. However, one problem is that learning is very slow, and sometimes ambiguous final representations are obtained. To remedy these shortcomings, we introduce a new activation function, that is, Gaussian activation functions for competitive units. By changing a parameter for the Gaussian activation functions, we can build a network that does not focus on faithful representations of input patterns, but try to extract the main characteristics of input patterns. Because this method are not concerned with detailed parts of input patterns, learning is significantly accelerated and salient features should be extracted. We applied the method to a road classification problem. Experimental results confirmed that learning was significantly accelerated and salient features could be extracted.
The social navigation types that include recommendations and guides were discussed. The systems goal was to increase visual awareness of social cues that exist in the information space, without levying the final decis...
详细信息
The social navigation types that include recommendations and guides were discussed. The systems goal was to increase visual awareness of social cues that exist in the information space, without levying the final decision on the user. Recommendation systems include computed information that help in guiding the users.
In this paper, we introduce Block Jam, a Tangible User Interface that controls a dynamic polyrhythmic sequencer using 26 physical artifacts. These physical artifacts, that we call blocks, are a new type of input devic...
详细信息
In this paper, we propose a new information theoretic method for self-organizing maps. The method aims to control competitive processes flexibly, that is, to produce different competitive unit activations according to...
详细信息
In this paper, we propose a new information theoretic method for self-organizing maps. The method aims to control competitive processes flexibly, that is, to produce different competitive unit activations according to information content obtained in learning. Competition is realized by maximizing mutual information between input patterns and competitive units. Competitive unit outputs are computed by the inverse of distance between input patterns and competitive unit. As distance is smaller, a neuron tends to fire strongly. Thus, winning neurons represent faithfully input patterns. We applied our method to a road classification problem. Experimental results confirmed that the new method could produce more explicit self-organizing maps than conventional self-organizing methods.
The article discusses an autonomous robot for the AAAI Robot Challenge. In an attempt to solve as much of the AAAI Robot Challenge as possible, five research institutions representing academia, industry and government...
详细信息
The article discusses an autonomous robot for the AAAI Robot Challenge. In an attempt to solve as much of the AAAI Robot Challenge as possible, five research institutions representing academia, industry and government integrated their research into a single robot named Grace. The article describes the first-year effort by the Grace team, including not only the various techniques each participant brought to Grace but also the difficult integration effort itself.
The literature on information visualization establishes the usability of interfaces with an overview of the information space, but for zoomable user interfaces, results are *** compare zoomable user interfaces with an...
详细信息
During the last years, the significant increase of mobile communications has resulted in the wide acceptance of a plethora of new services, like communication via written short messages (SMS). The limitations of the d...
详细信息
Spinner, a media collection, interaction and sharing device for early learners is studied. It promotes play and exploration using a novel set of interactive techniques and designs based around a non sequential, contex...
详细信息
ISBN:
(纸本)1581134541
Spinner, a media collection, interaction and sharing device for early learners is studied. It promotes play and exploration using a novel set of interactive techniques and designs based around a non sequential, contextual physical interface and a graphical user interface (GUI). It consists of a device, 3 types of input modules and two connector ports for the modules.
In this paper, we extend our greedy information algorithm to multi-layered networks for improved feature detection. We have developed a new information theoretic network-growing model called greedy information acquisi...
详细信息
In this paper, we extend our greedy information algorithm to multi-layered networks for improved feature detection. We have developed a new information theoretic network-growing model called greedy information acquisition. The method have shown good performance in extracting salient features in input patterns. However, because networks used in the method are single-layered ones, it has shown some difficulty in dealing with complex problems. In this context, we extend our greedy information acquisition method to multi-layered networks. By multi-layered networks, we can solve many complex problems that single-layered networks fail to do. The new algorithm was applied to two problems: the famous vertical-horizontal lines detection and a drive scene classification problem. In both cases, experimental results confirmed that our method could solve complex problems that single-layered networks fail to do. In addition, information maximization makes it possible to extract salient features in input patterns. The new algorithm can certainly contribute to the extension of neural computing.
暂无评论