This paper describes a single transistor floating-gate synapse device that can be used to store a weight in a nonvolatile manner, compute a biological EPSP, and demonstrate biological learning rules such as Long-Term Potentiation, LTD, and spike-time dependent plasticity. We also describe a highly scalable architecture of a matrix of synapses to implement the described learning rules. Parameters for weight update in the 0.35 um process have been extracted and can be used to predict the change in weight based on time difference between pre- and post-synaptic spike times.
We present a Aoaung-gale based system for computing vector quantization (VQ), which is typically used for data compression and cl&ssificalion o f signals to symbols. We present an architecture and resulting circcu~ts which will enable direcrprogramming/srorage of weight YZCIO~S, 8. 5 well m methods for adaptive VQ. We UEC an analog bump circuit to perform P continuous distance compul;ltion along a particular input coordinvre. Unlike II liaditional bump circuit, we use differential Boating-gale iriputs to provide the abilily 10 store the learned value. Thhe current outputs of each bump circuit are summed dong il single wire, where [he largest result(s) ace srlecred using B winner-take-ail circuit. We present experimental results measured from ICs fabricated on a O . k m CMOS process available through MOSIS.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.