arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.08149quant-phcs.OH
收藏

量子退火回忆下联想记忆的指数容量

Exponential capacity of associative memories under quantum annealing recall

Siddhartha Santra, Omar Shehab, Radhakrishnan Balu

摘要:

在理论神经科学和计算机科学中,联想记忆模型通常可以存储次线性数量的记忆。我们发现,使用量子退火回忆任务赋予联想记忆模型的指数存储容量。理论上,我们得到了这种方案的吸引域半径$R(N)$和容量$C(N)$,以及它们之间的折衷.我们的计算表明,对于随机选择的记忆,使用Hebbian学习规则并通过量子退火召回的模型的容量在问题的大小$C(N)=\mathcal{O}(e^{C_1N}),~C_1\geq0$上是指数级的,并且在随机选择的记忆集上成功的概率为$(1-e^{-C_2N}),~C_2\geq0$和$C_1+C_2=(.5-f)^2/(1-f)$,其中,$f=R(N)/N,~0\leq f\leq .5$是根据输入探针与存储的存储器的汉明距离的吸引半径,作为问题大小的一部分。我们演示了该方案的应用程序上的可编程量子退火设备-Dwave处理器。

英文摘要:

Associative memory models, in theoretical neuro- and computer sciences, can generally store a sublinear number of memories. We show that using quantum annealing for recall tasks endows associative memory models with exponential storage capacities. Theoretically, we obtain the radius of attractor basins, $R(N)$, and the capacity, $C(N)$, of such a scheme and their tradeoffs. Our calculations establish that for randomly chosen memories the capacity of a model using the Hebbian learning rule with recall via quantum annealing is exponential in the size of the problem, $C(N)=\mathcal{O}(e^{C_1N}),~C_1\geq0$, and succeeds on randomly chosen memory sets with a probability of $(1-e^{-C_2N}),~C_2\geq0$ with $C_1+C_2=(.5-f)^2/(1-f)$, where, $f=R(N)/N,~0\leq f\leq .5$ is the radius of attraction in terms of Hamming distance of an input probe from a stored memory as a fraction of the problem size. We demonstrate the application of this scheme on a programmable quantum annealing device - the Dwave processor.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑