Using graph theoretic measures to predict the performance of associative memory models
Calcraft, L.; Adams, R.G.; Chen, W.; Davey, N.
Citation: Calcraft , L , Adams , R G , Chen , W & Davey , N 2008 , ' Using graph theoretic measures to predict the performance of associative memory models ' . in ESANN2008: 16th European Symposium on Artificial Neural Networks . ESANN , pp. 107-112 .
We test a selection of associative memory models built with different connection strategies, exploring the relationship between the structural properties of each network and its pattern-completion performance. It is found that the Local Efficiency of the network can be used to predict pattern completion performance for associative memory models built with a range of different connection strategies. This relationship is maintained as the networks are scaled up in size, but breaks down under conditions of very sparse connectivity.
Original paper can be found at: http://www.dice.ucl.ac.be/esann/proceedings/electronicproceedings.htm