Dipartimento di Fisica, Università degli Studi di Parma, viale Usberti 7/A, 43100 Parma, Italy.
Phys Rev Lett. 2012 Dec 28;109(26):268101. doi: 10.1103/PhysRevLett.109.268101. Epub 2012 Dec 26.
We introduce a bipartite, diluted and frustrated, network as a sparse restricted Boltzmann machine and we show its thermodynamical equivalence to an associative working memory able to retrieve several patterns in parallel without falling into spurious states typical of classical neural networks. We focus on systems processing in parallel a finite (up to logarithmic growth in the volume) amount of patterns, mirroring the low-level storage of standard Amit-Gutfreund-Sompolinsky theory. Results obtained through statistical mechanics, the signal-to-noise technique, and Monte Carlo simulations are overall in perfect agreement and carry interesting biological insights. Indeed, these associative networks pave new perspectives in the understanding of multitasking features expressed by complex systems, e.g., neural and immune networks.
我们引入了一个二部、稀释和受挫的网络，将其作为稀疏受限玻尔兹曼机，并展示了它与联想工作记忆的热力学等价性，联想工作记忆能够并行检索多个模式，而不会陷入经典神经网络中典型的虚假状态。我们专注于并行处理有限数量（数量随体积呈对数增长）的模式的系统，反映了 Amit-Gutfreund-Sompolinsky 标准理论的底层存储。通过统计力学、信噪比技术和蒙特卡罗模拟得到的结果总体上完全一致，并具有有趣的生物学见解。事实上，这些联想网络为理解复杂系统（例如神经和免疫网络）表达的多任务特征开辟了新的视角。
