TAILIEUCHUNG - New Developments in Robotics, Automation and Control 2009 Part 10

Tham khảo tài liệu 'new developments in robotics, automation and control 2009 part 10', kỹ thuật - công nghệ, cơ khí - chế tạo máy phục vụ nhu cầu học tập, nghiên cứu và làm việc hiệu quả | Kohonen Feature Map Associative Memory with Refractoriness based on Area Representation 263 Layer the output of the neuron i in the Map-Layer x m a is calculated by maP _ Xi 1 0 if d x Wi 0b a otherwise 10 where 0 p is the threshold of the neuron in the Map-Layer as follows 0 - dmin a dmax - dm 11 d min 111111 d x Wi 12 dmax maxd x Wi 13 In Eq. 11 a 0 a is the coefficient. Then the output of the neuron k in the I O-Layer x is calculated as follows n 11 if u 0 xk I 0 otherwise u 1 y Wik k map ik y xi i xt 1 i 14 15 where 0bi is the threshold of the neuron in the I O-Layer uki is the internal state of the neuron k in the I O-Layer. Recall Process for Analog Patterns In the recall process of the KFM-AR when the analog pattern x is given to the I O-Layer the output of the neurons i in the Map-Layer ximap is calculated by xi 1 0 if d x W 9a otherwise 16 where 0a is the threshold of the neuron in the Map-Layer. Then the output of the neuron k in the I O-Layer x is calculated as follows X vW EWk y xi i Xi 1 . i 17 264 New Developments in Robotics Automation and Control 3. KFM Associative Memory with Refractoriness based on Area Representation The conventional KFM associative memory Ichiki et al. 1993 and KFMAM-AR Abe Osana 2006 cannot realize one-to-many associations. In this paper we propose the Kohonen Feature Map Associative Memory with Refractoriness based on Area Representation KFMAM-R-AR which can realize one-to-many associations. The proposed model is based on the KFMAM-AR and the neurons in the Map-Layer have refractoriness. In the proposed model one-to-many associations are realized by the refractoriness of neurons. On the other hand although the conventional KFMAM-AR can realize associations for analog patterns it does not have enough robustness for damaged neurons. In this research the model which has enough robustness for damaged neurons when analog patterns are memorized is realized by improvement of the calculation of the internal states of .

TỪ KHÓA LIÊN QUAN
Đã phát hiện trình chặn quảng cáo AdBlock
Trang web này phụ thuộc vào doanh thu từ số lần hiển thị quảng cáo để tồn tại. Vui lòng tắt trình chặn quảng cáo của bạn hoặc tạm dừng tính năng chặn quảng cáo cho trang web này.