2011/03/06 by Farnood Merrikh-Bayat, Merrikh-Bayat, Farnood, Saeed Bagheri Shouraki +2
Computer Science · Engineering · Neuroscience · #Advanced Memory and Neural Computing #Artificial Intelligence (cs.AI) #CCD and CMOS Imaging Sensors #FOS: Computer and information sciences #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function #cs.AI #cs.NE
paper · pdf · doi:10.48550/arxiv.1103.1156
34 pages, 14 figures, Submitted to IEEE Transactions on Fuzzy Systems
arxiv created 2011/03/06 · openalex publication_date 2011/03/06 · arxiv updated 2011/03/08 · openalex created_date 2022/10/01 · openalex updated_date 2026/07/28
In this paper a novel neuro-fuzzy system is proposed where its learning is\nbased on the creation of fuzzy relations by using new implication method\nwithout utilizing any exact mathematical techniques. Then, a simple memristor\ncrossbar-based analog circuit is designed to implement this neuro-fuzzy system\nwhich offers very interesting properties. In addition to high connectivity\nbetween neurons and being fault-tolerant, all synaptic weights in our proposed\nmethod are always non-negative and there is no need to precisely adjust them.\nFinally, this structure is hierarchically expandable and can compute operations\nin real time since it is implemented through analog circuits. Simulation\nresults show the efficiency and applicability of our neuro-fuzzy computing\nsystem. They also indicate that this system can be a good candidate to be used\nfor creating artificial brain.\n