• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.364-370
• /
• 2005

LBL(Layer-By-Layer) algorithms have been proposed to accelerate the training speed of MLPs(Multilayer Perceptrons). In this LBL algorithms, each layer needs a error function for optimization. Especially, error function for hidden layer has a great effect to achieve good performance. In this sense, this paper proposes a new hidden layer error function for improving the performance of LBL algorithm for MLPs. The hidden layer error function is derived from the mean squared error of output layer. Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.

• The Journal of the Korea Contents Association
• /
• v.5 no.6
• /
• pp.57-64
• /
• 2005

LBL(Layer-By-Layer) algorithms have been proposed to accelerate the training speed of MLPs(Multilayer Perceptrons). In this LBL algorithms, each layer needs a error function for optimization. Especially, error function for hidden layer has a great effect to achieve good performance. In this sense, this paper proposes a new hidden layer error function for improving the performance of LBL algorithm for MLPs. The hidden layer error function is derived from the mean squared error of output layer. Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.

• Korean Institute of Interior Design Journal
• /
• v.20 no.6
• /
• pp.161-172
• /
• 2011

Although the term royal floors is broadly used in high-rise housing, it is hard to find any clear scholarly definition of this term or any in-depth study exploring people's perceptions of it. This study reviewed ongoing discussions about concepts and definitions regarding royal floors, collected opinions from high-rise housing residents and realtors about the term, and compared the opinions of these two groups. First, the statistically analyzed results verified five main factors affecting people's perceptions of royal floors: locational characteristics (i.e., daylight, view, orientation), 2) price characteristics (i.e., premium, price increase level, number of houses on urgent sale), 3) best location of apartment building (i.e., location within a neighborhood, unit size), 4) architectural characteristics of apartment complex (i.e., size of complex, housing type, size options of units), and 5) personal characteristics of respondents (i.e., personal concepts of the meaning of housing, lifestyles). Results from the analysis showed that realtors perceived strong relationships between royal floors and 1) locational and 2) price characteristic factors, while residents perceived strong relationships between royal floors and personal preference as well as three factors from the five identified above: 1) locational, 2) price, and 4) architectural characteristics. Third, in defining royal floors in a building, the past rule of 1/4 is no longer effective. Instead, the rule of 1/n has become more prevalent (i.e., 1/6 to 1/8). Fourth, royal floors can be defined as the 15th to 25th floors in a 30-story high-rise housing structure based on the agreement of 50% of residents and 70% of realtors.