#### Filter Results:

- Full text PDF available (3)

#### Publication Year

1999

2008

- This year (0)
- Last 5 years (0)
- Last 10 years (1)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

A multilayer perceptron is usually considered a passive learner that only receives given training data. However, if a multilayer perceptron actively gathers training data that resolve its uncertainty about a problem being learnt, sufficiently accurate classification is attained with fewer training data. Recently, such active learning has been receiving an… (More)

We propose a learning algorithm for selforganizing neural networks to form a topology preserving map from an input manifold whose topology may dynamically change. Experimental results show that the network using the proposed algorithm can rapidly adjust itself to represent the topology of nonstationary input distributions. key words: competitive Hebbian… (More)

- Hiroyuki Takizawa, Taira Nakajima, Kentaro Sano, Hiroaki Kobayashi
- Applied Informatics
- 2003

In this paper, we propose an efficient method for tracking multiple objects, which deals with occlusion situations in an image. We use Shape from silhouettes method to reconstruct objects 3D position from images taken from different directions. Then we track the objects' reconstructed 3D positions by using mixed-state CONDENSATION algorithm. The… (More)

- Taira Nakajima
- FECS
- 2008

- Taira Nakajima
- Computational Intelligence
- 2005

- Kentaro Sano, Shintaro Momose, +4 authors Tadao Nakamura
- IASTED PDCS
- 2002

- ‹
- 1
- ›