The structure of Chinese characters is reviewed and seen to be best represented as a 3-layer hierarchy of character, radical and stroke. Fuzzy possibilistic reasoning is then put forward as an appropriate set of conceptual tools to investigate the automatic recognition of these characters. Associative memory artificial neural network algorithms form a suitable technique for realising these conc...

Chartier and his colleagues have recently proposed a nonlinear synchronous attractor neural network. In the Nonlinear Dynamic Recurrent Associative Memory (NDRAM), learning has been shown to converge to a set of real-valued attractors in single-layered neural networks and bidirectional associative memories. However, the transmission is highly nonlinear and its global stability has never been an...

In this paper, the existence and uniqueness of the equilibrium point and its global asymptotic stability are discussed for a general class of recurrent neural networks with time-varying delays and Lipschitz continuous activation functions. The neural network model considered includes the delayed Hopfield neural networks, bidirectional associative memory networks, and delayed cellular neural net...

In this paper, a five-neuron bidirectional associative memory (BAM) neural network with two time delays is studied. Since the study of Hopf bifurcation is very important for the design and application of BAM neural networks, we investigate that Hopf bifurcation occurs and a family of periodic solutions appear when the sum of two delays passes through a critical value.

The mid 20th century saw the publication of two pioneering works in the fields of neural networks and coding theory, respectively the work of McCulloch and Pitts in 1943, and the work of Shannon in 1948. The former paved the way for artificial neural networks while the latter introduced the concept of channel coding, which made reliable communication over noisy channels possible. Though seeming...

Accurate memory prefetching is paramount for processor performance, and modern processors employ various techniques to identify and prefetch different memory access patterns. While most modern prefetchers target spatio-temporal patterns by matching memory addresses that are accessed in close proximity (either in space or time), the recently proposed concept of semantic locality views locality a...

This paper proposes an intuitive real-time robot control system using human body movement. Recently, it has been developed that motion generation for humanoid robots with reflecting human body movement, which is measured by a motion capture. However, in the existing studies about robot control system by human body movement, the detailed structure information of a robot, for example, degrees of ...

Associative Morphological Memories are a recently proposed neural networks architecture based on the shift of the basic algebraic framework. They possess some robustness to specific noise models (erosive and dilative noise). Combining the Associative Morphological Memories with erosion/dilation scale-spaces, we achieved an increased robustness against noise. Here we report ongoing work on their...