White Rose Consortium ePrints Repository

In this paper we evaluate a selection of data retrieval algorithms for storage e ciency retrieval speed and partial matching capabilities using a large information retrieval dataset We evaluate standard data structures for example inverted le lists and hash tables but also a novel binary neu ral network that incorporates single epoch training superimposed coding and associative matching in a binary matrix data structure We identify the strengths and weaknesses of the approaches From our evaluation the novel neural network approach is superior with respect to training speed and partial match retrieval time From the results we make recommenda tions for the appropriate usage of the novel neural approach