mARC: Memory by Association and Reinforcement of Contexts
This addresses information classification and retrieval problems like e-Discovery, offering a potential improvement over existing systems, though it appears incremental as a new method applied to known bottlenecks.
The paper tackles the problem of data storage and retrieval by introducing mARC, a novel technology based on quantum mechanics, which in a demonstrator search engine outperforms Google by an order of magnitude in response time and provides more relevant results for some queries.
This paper introduces the memory by Association and Reinforcement of Contexts (mARC). mARC is a novel data modeling technology rooted in the second quantization formulation of quantum mechanics. It is an all-purpose incremental and unsupervised data storage and retrieval system which can be applied to all types of signal or data, structured or unstructured, textual or not. mARC can be applied to a wide range of information clas-sification and retrieval problems like e-Discovery or contextual navigation. It can also for-mulated in the artificial life framework a.k.a Conway "Game Of Life" Theory. In contrast to Conway approach, the objects evolve in a massively multidimensional space. In order to start evaluating the potential of mARC we have built a mARC-based Internet search en-gine demonstrator with contextual functionality. We compare the behavior of the mARC demonstrator with Google search both in terms of performance and relevance. In the study we find that the mARC search engine demonstrator outperforms Google search by an order of magnitude in response time while providing more relevant results for some classes of queries.