Stable fixed points of combinatorial threshold-linear networks
Stable fixed points of combinatorial threshold-linear networks
复制标题
组合阈值线性网络的稳定不动点
DOI:
10.1016/j.aam.2023.102652
复制
发表时间:
2024
影响因子:
1.1
通讯作者:
Morrison, Katherine
中科院分区:
文献类型:
--
作者:
Curto, Carina;Geneson, Jesse;Morrison, Katherine
Combinatorial threshold-linear networks (CTLNs) are a special class of recurrent neural networks whose dynamics are tightly controlled by an underlying directed graph. Recurrent networks have long been used as models for associative memory and pattern completion, with stable fixed points playing the role of stored memory patterns in the network. In prior work, we showed that target-free cliques of the graph correspond to stable fixed points of the dynamics, and we conjectured that these are the only stable fixed points possible [19],[8]. In this paper, we prove that the conjecture holds in a variety of special cases, including for networks with very strong inhibition and graphs of size n≤ 4. We also provide further evidence for the conjecture by showing that sparse graphs and graphs that are nearly cliques can never support stable fixed points. Finally, we translate some results from extremal combinatorics to obtain an upper bound on the number of stable fixed points of CTLNs in cases where the conjecture holds.
登录
查看更多内容
影响因子:
2.1
作者:
通讯作者:
--
影响因子:
--
作者:
Curto, Carina;Morrison, Katherine
通讯作者:
Morrison, Katherine
影响因子:
3.7
作者:
Parmelee C;Moore S;Morrison K;Curto C
通讯作者:
Curto C
影响因子:
2.9
作者:
Curto, Carina;Morrison, Katherine
通讯作者:
Morrison, Katherine
影响因子:
1.1
作者:
Tomita, Etsuji;Tanaka, Akira;Takahashi, Haruhisa
通讯作者:
Takahashi, Haruhisa