Spiking neuron network Helmholtz machine.
Spiking neuron network Helmholtz machine.
复制标题
DOI：
10.3389/fncom.2015.00046
复制
发表时间：
2015
影响因子：
3.2
通讯作者：
Miller P
中科院分区：
文献类型：
--
作者：
Sountsov P;Miller P
越来越多的行为和神经生理学数据表明，大脑在感知和其他任务期间执行最佳（或接近最佳）概率推理和学习。尽管存在许多以最佳方式执行推理和学习的机器学习算法，但如何在大脑中实现这些算法之一（或新颖算法）的完整描述目前还不完整。已经提出了许多解决神经元如何执行最佳推理的解决方案，但突触可塑性如何实现最佳学习的问题却很少得到解决。本文旨在通过使用现实模型尖峰神经元的神经元网络来统一概率推理和突触可塑性两个领域，以实现经过充分研究的称为亥姆霍兹机的计算模型。亥姆霍兹机适合神经实现，因为它用于学习其参数的算法（称为唤醒-睡眠算法）使用局部增量学习规则。我们的尖峰神经元网络同时实现了 Delta 规则和亥姆霍兹机的一个小例子。该神经元网络可以在没有监督的情况下学习连续值训练数据集的内部模型。网络还可以对学习到的内部模型进行推理。我们展示了神经实现的各种生物物理特征如何限制唤醒-睡眠算法的参数，例如学习的唤醒和睡眠阶段的持续时间以及最小样本持续时间。我们检查与最佳性能的偏差，并将它们与突触可塑性规则的属性联系起来。
An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule.
登录
查看更多内容
影响因子：
19.9
作者：
Fiser, Jozsef;Berkes, Pietro;Orban, Gergo;Lengyel, Mate
通讯作者：
Lengyel, Mate
DOI：
10.1073/pnas.0909394107
发表时间：
2010-03-09
影响因子：
11.1
作者：
D'Souza, Prashanth;Liu, Shih-Chii;Hahnloser, Richard H. R.
通讯作者：
Hahnloser, Richard H. R.
影响因子：
56.9
作者：
Blaisdell, AP;Sawa, K;Waldmann, MR
通讯作者：
Waldmann, MR
影响因子：
2.9
作者：
DAYAN, P;HINTON, GE;ZEMEL, RS
通讯作者：
ZEMEL, RS
影响因子：
1.8
作者：
Atkins, JE;Fiser, J;Jacobs, RA
通讯作者：
Jacobs, RA