ICONIP
2008
13 years 10 months ago
2008
Abstract. We previously proposed a neural segmentation model suitable for implementation with complementary metal-oxide-semiconductor (CMOS) circuits. The model consists of neural ...
ICONIP
2008
13 years 10 months ago
2008
Asbestos-related illnesses become a nationwide problem in Japan. Now human inspectors check whether asbestos is contained in building material or not. To judge whether the specimen...
ICONIP
2008
13 years 10 months ago
2008
Abstract. Feature selection has improved the performance of text clustering. Global feature selection tries to identify a single subset of features which are relevant to all cluste...
ICONIP
2008
13 years 10 months ago
2008
Abstract. The concept of Ensemble Learning has been shown to increase predictive power over single base learners. Given the bias-variancecovariance decomposition, diversity is char...
ICONIP
2008
13 years 10 months ago
2008
Several applications would emerge from the development of efficient and robust sound classification systems able to identify the nature of non-speech sound sources. This paper prop...
ICONIP
2008
13 years 10 months ago
2008
We present a system for regression using MLP neural networks with hyperbolic tangent functions in the input, hidden and output layer. The activation functions in the input and outp...
ICONIP
2008
13 years 10 months ago
2008
Abstract. While injecting fault during training has long been demonstrated as an effective method to improve fault tolerance of a neural network, not much theoretical work has been...
ICONIP
2008
13 years 10 months ago
2008
Abstract. Internet literature queries return a long lists of citations, ordered according to their relevance or date. Query results may also be represented using Visual Language th...
ICONIP
2008
13 years 10 months ago
2008
Abstract. Face perception and text reading are two of the most developed visual perceptual skills in humans. Understanding which features in the respective visual patterns make the...
ICONIP
2008
13 years 10 months ago
2008
Practical Recurrent Learning (PRL) has been proposed as a simple learning algorithm for recurrent neural networks[1][2]. This algorithm enables learning with practical order O(n2 )...