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
Wildlife species such as tigers and elephants are under the threat of poaching. To combat poaching, conservation agencies (“defenders”) need to (1) anticipate where the poachers are likely to poach and (2) plan effective patrols. We propose an anti-poaching tool CAPTURE (Comprehensive Anti-Poaching tool with Temporal and observation Uncertainty REasoning),(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)
Word learning has been a hot issue in cognitive science for many years. So far there are mainly two theories on it, hypothesis elimination and associative learning, yet none of them could explain the recognized experiments approvingly. By integrating advantages of these two approaches, a Bayesian inference framework was proposed recently, which fits some(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)
  • Fukang Fang
  • 2005 International Conference on Neural Networks…
  • 2005
Several issues related to learning process are discussed from the viewpoint of self-organization in this paper. Though Hebbian rule and BCM rule are widely used in learning process, there may be a more general mechanism behind the rules and J structure with specific attractors may be such kind of mechanism. Chinese character learning is good example 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)
SOMs have been successfully applied in various fields. In this paper, we proposed an expanded SOM model for word learning which is a classic problem in cognitive science. In spite of simple computation of this model, the simulation results are consistent with the conclusion of the newest Bayesian model in the same learning cases. It implies that this model(More)
Synchronization is an important issue in neuroscience. It is still a problem in computational neuroscience to set and analyze synchronization models, especially the model with complex synaptic equations and burst type neurons. We try to use a new mathematical method and apply a Lyapunov function to the searching for the right synaptic equation, which would(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)