DocumentCode :
3633527
Title :
Influence of information leakage in analog memory on learning Kohonen network on silicon
Author :
Rafal Dlugosz;Tomasz Talaska;Ryszard Wojtyna
Author_Institution :
Institute of Microtechnology, Swiss Federal Institute of Technology in Lausanne (EPFL), Neuchatel, Switzerland
fYear :
2009
Firstpage :
282
Lastpage :
285
Abstract :
The paper presents an influence of leakage effect observed in capacitive analog memories on learning process in hardware implemented Kohonen neural networks with MOS transistors used as switches connected with information holding capacitors. The learning results, i.e. variations (adaptations) of weight values, strongly depend on the transistor leakage currents. This is a cause for some quantization error associated with the weight adaptations during the network training. The unwanted leakage influence can be minimized in several ways discussed in this paper. As expected, the observed leakage influence on the memory storage time rises with an increase of temperature. This has been verified by means of computer simulations (Matlab, HSpice) as well as measurements of a prototyped Kohonen network chip (0.18µm CMOS process).
Keywords :
"Analog memory","Silicon","Neural network hardware","Neural networks","MOSFETs","Switches","Switched capacitor networks","MOS capacitors","Leakage current","Quantization"
Publisher :
ieee
Conference_Titel :
Mixed Design of Integrated Circuits & Systems, 2009. MIXDES ´09. MIXDES-16th International Conference
Print_ISBN :
978-1-4244-4798-5
Type :
conf
Filename :
5289497
Link To Document :
بازگشت