基于启发式退火拓扑择优机制的稀疏联想记忆实现

借鉴统计物理学中的“退火”概念，针对已有稀疏互联联想记忆模型中只考虑网络连接随机稀疏方式，缺乏面向特定模式存储任务的确定性操作，使用非平衡态统计分析方法，讨论了有限代谢能量资源约束下的网络结构最优稀疏原则，给出了相应的理论推导.在此基础上，研究了面向特定学习任务的网络稀疏结构自适应方法，构建了基于启发式退火拓扑择优机制的稀疏联想记忆模型.实验表明，该模型既具有一定的生物学基础，维持了网络结构广泛稀疏互联的特性，又能在网络资源受限条件下达到最优联想记忆性能，符合神经生物系统本身自组织、自学习的特点.

Sparsely Connected Associative Memory Based on the Preferential Mechanism of Heuristic Annealed Topology

A novel sparsely connected associative memory based on the preferential mechanism of heuristic annealed topology was proposed in this paper. Aimed at overcoming the disadvantage of quenched dilution as random synapses disconnection of the existing methods, this model, taking the ideology of annealed dilution of statistical physics into account, investigates the optimal synaptic dilution strategy under the constraints of limited metabolic energy, namely limited amount of neurons and connections. Based on explicit theoretical analysis, this model constructs a learning task-dependent network topology in a heuristic annealed way which is much closer to biological genuine system as possessing flexible adaptive topology. It can achieve better performance than the existing counterparts of the same class. The effectiveness and robustness of the proposed model is validated by a great number of experiments.