Sciweavers

ICONIP
2007
13 years 6 months ago
Policy Learning for Motor Skills
Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, ...
Jan Peters, Stefan Schaal
ICONIP
2007
13 years 6 months ago
Dynamical Nonstationarity Analysis of Resting EEGs in Alzheimer's Disease
The understanding of nonstationarity, from both a dynamical and a statistical point of view, has turned from a constraint on application of a specific type of analysis (e.g. spectr...
Charles-Francois Vincent Latchoumane, Emmanuel C. ...
ICONIP
2007
13 years 6 months ago
A Kolmogorov-Smirnov Correlation-Based Filter for Microarray Data
Abstract. A filter algorithm using F-measure has been used with feature redundancy removal based on the Kolmogorov-Smirnov (KS) test for rough equality of statistical distribution...
Jacek Biesiada, Wlodzislaw Duch
ICONIP
2007
13 years 6 months ago
Neural Decoding of Movements: From Linear to Nonlinear Trajectory Models
To date, the neural decoding of time-evolving physical state – for example, the path of a foraging rat or arm movements – has been largely carried out using linear trajectory m...
Byron M. Yu, John P. Cunningham, Krishna V. Shenoy...
ICONIP
2007
13 years 6 months ago
RNN with a Recurrent Output Layer for Learning of Naturalness
– The behavior of recurrent neural networks with a recurrent output layer (ROL) is described mathematically and it is shown that using ROL is not only advantageous, but is in fac...
Ján Dolinský, Hideyuki Takagi
ICONIP
2007
13 years 6 months ago
Practical Recurrent Learning (PRL) in the Discrete Time Domain
One of the authors has proposed a simple learning algorithm for recurrent neural networks, which requires computational cost and memory capacity in practical order O(n2 )[1]. The a...
Mohamad Faizal Bin Samsudin, Takeshi Hirose, Katsu...
ICONIP
2007
13 years 6 months ago
A System Model for Real-Time Sensorimotor Processing in Brain
Abstract. The present paper addresses a general diagram to investigate the real-time parallel computation mechanism in the brain, using an idea of “Gantt chart.” This diagram e...
Yutaka Sakaguchi
ICONIP
2007
13 years 6 months ago
Using Image Stimuli to Drive fMRI Analysis
We introduce a new unsupervised fMRI analysis method based on Kernel Canonical Correlation Analysis which differs from the class of supervised learning methods that are increasing...
David R. Hardoon, Janaina Mourão Miranda, M...
ICONIP
2007
13 years 6 months ago
The Detection of an Approaching Sound Source Using Pulsed Neural Network
Current automobiles’ safety systems based on video cameras and movement sensors fail when objects are out of the line of sight. This paper proposes a system based on pulsed neura...
Kaname Iwasa, Takeshi Fujisumi, Mauricio Kugler, S...