Fukang Fang

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
—As we know, there is a debate on the mode of visual perception for a long time, that is, does the visual system acquire percept from local to global or from global to local. A three-layer perceptual model with function of signal decomposition and integration is developed, and Chinese character grapheme is chosen to train the model. The model is trained(More)
The functions of neural system, such as learning, recognition and memory, are the emergences from the elementary dynamic mechanisms. To discuss how the dynamic mechanisms in the neurons and synapses work in the function of recognition, a dynamic neural circuit is designed. In the neural circuit, the information is expressed as the inter-spike intervals of(More)
The cognition and learning of Chinese characters is a good example of human visual perception and learning. The synchronization behavior between neuronal groups in cortical areas is one of the core mechanisms in visual image perception and recognition. We built a neural network with locally coupled Wilson-Cowan oscillators to learn Chinese characters.(More)
In this paper, we explore the recognition of polyphone. The cognition process is complex, which needs other additional information, otherwise it may cause uncertainty in decision. Recent research is almost focused on phonetics, while we plan to explore the question with neu-ral networks. H. Haken used synergetic neural network to discuss the recognition of(More)
Compounds are very common in many kinds of language. Most of the research in this field is from the view of morphology, while artificial neural network is seldom concerned. Based on Hopfield model, we create a novel neural network to simulate the recognition process of compounds in English and Chinese. Our model is composed of two layers: abstraction layer(More)
Dynamic neural networks are designed to discuss how the dynamic mechanisms in the neurons and synapses work in recognizing interspike intervals (ISIs). The threshold integration of post-synaptic membrane potentials, the refractory period of neurons, together with the spike-time-dependent plasticity (STDP) learning rule are discussed. Based on these dynamic(More)
To explore some mechanisms of generalization in concept formation, we build a Three-layer neural network with feedback and Hebbian learning rules. Using binary sequences as input, we simulate the generalization process from multiple examples to a concept. After tens of training, the outputs of the network will converge to stable states which denote the(More)
The formation of concepts is a key point in development of human intelligence. There are two kinds of traditional ideas about this problem: hypothesis elimination and associative learning. The Bayesian framework suggested by Tenenbaum absorbs the virtue and avoids the limitations of the two traditional ideas and its results are demonstrated by behavioral(More)
There is a key problem that how brain uses the properties of synaptic dynamics to implement its macro-functions. The dynamic synapse model made by J. S. Liaw and T. W. Berger provided an example of implementing speech recognition function with dynamic synaptic mechanisms. The emergence mechanisms of recognition function in the dynamic synapse model are(More)