• Citations Per Year
Learn More
We present a new approach for online incremental word acquisition and grammar learning by humanoid robots. Using no data set provided in advance, the proposed system grounds language in a physical context, as mediated by its perceptual capacities. It is carried out using show-and-tell procedures, interacting with its human partner. Moreover, this procedure(More)
This is a feasibility study of the implementation of discrete time cellular neural network (DT-CNN) annealing on Cellular AutoMata on Content Addressable Memory (CAM<sup>2</sup>). CAM<sup>2</sup> is a dedicated hardware for cellular automata (CA) and DT-CNN. We propose an annealing method on DT-CNN to solve quadratic assignment problems. This method uses(More)
This paper is first report of implementation of CNN on CAM<sup>2</sup>. CAM<sup>2</sup> is a highly-parallel two-dimensional cellular automata architecture. Due to digital circuitry restriction, CNN on CAM<sup>2</sup> operates as a discrete time CNN (DT-CNN), and each cell has quantized output function. In spite of such a restriction, we experimentally(More)
The goal of our research is to discover factors which predict which words will become buzzwords–terms representing topics that have become popular–within the blogosphere. In this paper, we propose a method which evaluates bloggers’ buzzword prediction ability by analyzing how early bloggers mentioned past buzzwords. We do so by measuring how early a(More)
  • 1