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, ...
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. ...
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...
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...
– 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...
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...
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...
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...
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...