Learn More
Some of non-manual signals (NMS's) are considered to be functioning as grammatical markers in JSL. To describe NMS's of Japanese Sign Language (JSL), we have developed a notational system that we named sIGNDEX Ver.2. We code NMS's which appear in 100 elicited utterances with this system. We analyze the data thus coded and find frequency of each NMS. Our(More)
As part of the undergraduate curricular reform at our university, we have begun offering on a trial basis a workshop course in which we introduce the concept of barrier-free engineering. There, the students partake in a group design project with the aim of creating a robot hand that can 'communicate' by movement; the long-term goal from the faculty research(More)
A method to speed-up the learning processes proposed in [1] using the GPGPU technology is proposed. The method in [1] is called the deep learning method (Deep LM), and a multilayer perceptron (MLP) which has successfully trained using the Deep LM is tolerant to multiple weight and neuron faults where the weight faults are between the hidden and output(More)