“忘却”可增加内容可寻址存储器的存储容量。
"Unlearning" increases the storage capacity of content addressable memories.
作者信息
Kleinfeld D, Pendergraft D B
出版信息
Biophys J. 1987 Jan;51(1):47-53. doi: 10.1016/S0006-3495(87)83310-6.
Abstract
The storage and retrieval of information in networks of biological neurons can be modeled by certain types of content addressable memories (CAMs). We demonstrate numerically that the amount of information that can be stored in such CAMs is substantially increased by an unlearning algorithm. Mechanisms for the increase in capacity are identified and illustrated in terms of an energy function that describes the convergence properties of the network.
摘要
生物神经元网络中信息的存储和检索可以通过某些类型的内容可寻址存储器（CAM）来建模。我们通过数值证明，一种遗忘算法可大幅增加此类CAM中可存储的信息量。从描述网络收敛特性的能量函数角度，识别并说明了容量增加的机制。
相似文献
1
"Unlearning" increases the storage capacity of content addressable memories.“忘却”可增加内容可寻址存储器的存储容量。
Biophys J. 1987 Jan;51(1):47-53. doi: 10.1016/S0006-3495(87)83310-6.
2
'Unlearning' has a stabilizing effect in collective memories.“忘却”对集体记忆具有稳定作用。
Nature. 1983;304(5922):158-9. doi: 10.1038/304158a0.
3
A hybrid neural network of addressable and content-addressable memory.一种可寻址和内容可寻址存储器的混合神经网络。
Int J Neural Syst. 2003 Jun;13(3):205-13. doi: 10.1142/S0129065703001546.
4
Spin glass model of learning by selection.通过选择进行学习的自旋玻璃模型。
Proc Natl Acad Sci U S A. 1986 Mar;83(6):1695-8. doi: 10.1073/pnas.83.6.1695.
5
Associative memory neural network with low temporal spiking rates.具有低时间尖峰率的联想记忆神经网络。
Proc Natl Acad Sci U S A. 1989 Oct;86(20):7871-5. doi: 10.1073/pnas.86.20.7871.
6
[Memory model based on the plasticity of inhibiting neurons].基于抑制性神经元可塑性的记忆模型
Biofizika. 1983 May-Jun;28(3):475-80.
7
Adaptive thresholds for neural networks with synaptic noise.具有突触噪声的神经网络的自适应阈值
Int J Neural Syst. 2007 Aug;17(4):241-52. doi: 10.1142/S012906570700110X.
8
Supervised perceptron learning vs unsupervised Hebbian unlearning: Approaching optimal memory retrieval in Hopfield-like networks.监督感知机学习与无监督海伯无学习：在类似 Hopfield 的网络中接近最佳记忆检索。
J Chem Phys. 2022 Mar 14;156(10):104107. doi: 10.1063/5.0084219.
9
Dynamics of the CA3 pyramidal neuron autoassociative memory network in the hippocampus.海马体中CA3锥体神经元自联想记忆网络的动力学
Philos Trans R Soc Lond B Biol Sci. 1994 Jan 29;343(1304):167-87. doi: 10.1098/rstb.1994.0019.
10
A modular attractor associative memory with patchy connectivity and weight pruning.具有斑块连接和权值修剪的模块化吸引子联想记忆。
Network. 2013;24(4):129-50. doi: 10.3109/0954898X.2013.859323.
本文引用的文献
1
Storing infinite numbers of patterns in a spin-glass model of neural networks.在神经网络的自旋玻璃模型中存储无限数量的模式。
Phys Rev Lett. 1985 Sep 30;55(14):1530-1533. doi: 10.1103/PhysRevLett.55.1530.
2
Spin-glass models of neural networks.神经网络的自旋玻璃模型。
Phys Rev A Gen Phys. 1985 Aug;32(2):1007-1018. doi: 10.1103/physreva.32.1007.
3
Neural networks and physical systems with emergent collective computational abilities.具有涌现集体计算能力的神经网络与物理系统。
Proc Natl Acad Sci U S A. 1982 Apr;79(8):2554-8. doi: 10.1073/pnas.79.8.2554.
4
'Unlearning' has a stabilizing effect in collective memories.“忘却”对集体记忆具有稳定作用。
Nature. 1983;304(5922):158-9. doi: 10.1038/304158a0.
5
The function of dream sleep.梦睡眠的功能。
Nature. 1983;304(5922):111-4. doi: 10.1038/304111a0.
6
Collective properties of neural networks: a statistical physics approach.神经网络的集体特性：一种统计物理学方法。
Biol Cybern. 1984;50(1):51-62. doi: 10.1007/BF00317939.
7
Neurons with graded response have collective computational properties like those of two-state neurons.具有分级反应的神经元具有与双态神经元类似的集体计算特性。
Proc Natl Acad Sci U S A. 1984 May;81(10):3088-92. doi: 10.1073/pnas.81.10.3088.
8
Computing with neural circuits: a model.利用神经回路进行计算：一种模型。
Science. 1986 Aug 8;233(4764):625-33. doi: 10.1126/science.3755256.
9
A statistical theory of short and long term memory.
Behav Biol. 1975 Jun;14(2):115-33. doi: 10.1016/s0091-6773(75)90122-4.
Zotero 插件