Weight to Vision Neural Network Information Processing Influence Research

Abstract:

Many factors influence vision neural network information processing process, for example: Signal initial value, weight, time and number of learning. This paper discussed the importance of weight in vision neural network information processing process. Different weight values can cause different results in neural networks learning. We structure a vision neural network model with three layers based on synapse dynamics at first. Then we change the weights of the vision neural network model’s to make the three layers a neural network of learning Chinese characters. At last we change the initial weight distribution to simulate the neural network of process of the learning Chinese words. Two results are produced. One is that weight plays a very important role in vision neural networks learning, the other is that different initial weight distributions have different results in vision neural networks learning.

• Periodical: Advanced Materials Research (Volumes 605-607)
• Pages: 2131-2136
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.605-607.2131
• Online since: December 2012
• Authors: Chun Hua Yin, Jia Wei Chen, Lei Chen
• Keywords: Learning, Model, Neural Network (NN), Weight

References

[1] Liaw J S, Berger T W. Dynamic synapse: Harnessing the computing power of synaptic dynamics. Neurocomputing. 1999, 26-27: 199-206.

DOI: 10.1016/s0925-2312(99)00063-6

[2] Daniel D L, Seung H. S. Learning the parts of objects by non-negative matrix factorization. Nature, 1999, 401(21): 788-791.

DOI: 10.1038/44565

[3] Babloyantz A. Self-Organization, Emerging Properties, and Learning, NATO ASI Series B: physics, Plenum Press: New York and London, (1991).

DOI: 10.1007/978-1-4615-3778-6

[4] Haken H. Principles of Brain Functioning: A Synergetic Approach to Brain Activity, Behavior and Cognition. Berlin: Springer, (1996).

[5] Kohonen T. The Self-Organizing Map. Springer-Verlag. 2nd edition. (1997).

[6] Izhikevich E M. Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting. MIT press, in press. (2006).

[7] Haken H. Brain Dynamics: Synchronization and Activity Pattern in Pulse-Couples Neural Nets with Delays and noise. Berlin: Springer, (2002).

DOI: 10.1007/978-3-540-46284-2