Abstract
This paper presents a new architecture of neural networks - intelligence increasing neural network (IINN). Formed surrounding the center of knowledge system, this neural network achieves the building, memory and use of the data base with clear structure. It obtains good classification results with more clear-cut meaning than other neural networks', using a discrimination principle based on Bayesian maximum posterior probability, the method of data extraction and reasonable optimization algorithm. IINN has a data base increasing dynamically, whose scale has a logarithmic connection with the number of the dividing classes. The belief degree of the data base converges in probability and the problem of over training does not exist. The comparison with the classification results of AdaBoost method indicates that when weak learners are independent, IINN has better performance than AdaBoost.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
