首页> 外文学位 >Capacity analysis of attractor neural networks with binary neurons and discrete synapses.

【24h】

Capacity analysis of attractor neural networks with binary neurons and discrete synapses.

机译：具有二元神经元和离散突触的吸引神经网络的容量分析。

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

We define the memory capacity of networks of binary neurons with finite-state synapses in terms of retrieval probabilities of learned patterns under standard asynchronous dynamics with a predetermined threshold. The threshold is set to control the proportion of non-selective neurons that fire. An optimal inhibition level is chosen to stabilize network behavior. For any local learning rule we provide a computationally efficient and highly accurate approximation to the retrieval probability of a pattern as a function of its age. The method is applied to the sequential models (Fusi and Abbott, 2007) and meta-plasticity models (Fusi et al, 2005; Leibold and Kempter, 2008). We show that as the number of synaptic states increases, the capacity, as defined here, either plateaus or decreases. In the few cases where multi-state models exceed the capacity of binary synapse models the improvement is small.

机译：我们根据具有预定阈值的标准异步动力学下的学习模式的检索概率，来定义具有有限状态突触的二进制神经元网络的存储容量。设置阈值以控制激发的非选择性神经元的比例。选择最佳抑制级别以稳定网络行为。对于任何局部学习规则，我们都提供了一种计算有效且高度精确的近似值，该概率是模式的年龄的函数。该方法适用于顺序模型（Fusi和Abbott，2007）和亚塑性模型（Fusi等，2005； Leibold和Kempter，2008）。我们表明，随着突触状态数量的增加，容量（如此处定义）稳定或下降。在少数情况下，多状态模型超过了二进制突触模型的容量，改进很小。

著录项

作者
Huang, Yibi.;
展开▼
作者单位

The University of Chicago.;

展开▼
授予单位 The University of Chicago.;
学科 Statistics.
学位 Ph.D.
年度 2010
页码 109 p.
总页数 109
原文格式 PDF
正文语种 eng
中图分类宗教;
关键词

相似文献

外文文献
中文文献
专利

1. Discrete-Attractor-like Tracking in Continuous Attractor Neural Networks [J] . Fung Chi Chung Alan, Fukai Tomoki Physical review letters . 2019,第1期

机译：连续吸引子神经网络中的类似于离散吸引子的跟踪
2. Exponential stability analysis of quaternion-valued neural networks with proportional delays and linear threshold neurons: Continuous-time and discrete-time cases [J] . Neurocomputing . 2020,第Mara14期

机译：具有比例延迟和线性阈值神经元的四元数神经网络的指数稳定性分析：连续时间和离散时间情况
3. Analysis and synthesis of a class of discrete-time neural networks with multilevel threshold neurons [J] . Si J., Michel A.N. IEEE Transactions on Neural Networks . 1995,第1期

机译：一类具有多级阈值神经元的离散神经网络的分析与综合
4. Discrete Parallel-sequential Update Of Neural Networks With Adapting Synapses. [C] . Goles E., Institute of Electric and Electronic Engineer International Joint Conference on Neural Networks . 2001

机译：具有调整突触的神经网络的离散并行序列更新。
5. Advances in applied econometrics: Binary discrete choice models, artificial neural networks, and asymmetries in the FAST multistage demand system. [D] . Bergtold, Jason S. 2004

机译：应用计量经济学的进展：FAST多阶段需求系统中的二元离散选择模型，人工神经网络和不对称性。
6. Correction: Effective Visual Working Memory Capacity: An EmergentEffect from the Neural Dynamics in an Attractor Network [O] . Laura Dempere-Marco, David P. Melcher, Gustavo Deco -1

机译：更正：有效的视觉工作记忆容量：一个新兴从神经动力学在吸引网络效应
7. Statistical mechanics of attractor neural networks and self-consistent signal-to-noise analysis : analog neural networks with nonmonotonic transfer functions and enhancement of the storage capacity(New Developments in Statistical Physics Similarities in Diversities,YITP Workshop) [O] . Shiino Masatoshi, Fukai Tomoki 1993

机译：吸引子神经网络的统计力学和自洽的信噪分析：具有非单调传递函数并增强存储容量的模拟神经网络（多样性的统计物理相似性的新进展，YITP研讨会）
8. Dynamic Attractors and Basin Class Capacity in Binary Neural Networks. [R] . Dayhoff, J. E., Palmadesso, P. J. 1994

机译：二元神经网络中的动态吸引子和盆地类能力。

Capacity analysis of attractor neural networks with binary neurons and discrete synapses.

摘要

著录项

相似文献

相关主题

期刊订阅