arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv cond-mat/0608564cond-mat.dis-nn
收藏

神经网络的一种异突触学习规则

A Heterosynaptic Learning Rule for Neural Networks

Frank Emmert-Streib

摘要:

在这篇文章中,我们介绍了一种新的随机Hebb类神经网络的学习规则,是神经生物学的动机。该学习规则结合了无监督(赫布)和监督(强化)学习的特征,并且在修改突触时的时间点选择方面是随机的。此外,学习规则不仅影响突触前和突触后神经元之间的突触,这被称为同突触可塑性,而且还影响突触前和突触后神经元的更远的突触。这种更复杂的突触可塑性形式最近受到神经生物学的研究,称为异突触可塑性。我们证明了这种学习规则是有用的,在训练神经网络学习奇偶校验功能,包括异或(XOR)映射在多层前馈网络。我们发现,我们的随机学习规则工作良好,即使在噪声的存在。重要的是,平均学习时间随着要学习的模式的数量多项式地增加,表明有效的学习。

英文摘要:

In this article we intoduce a novel stochastic Hebb-like learning rule for neural networks that is neurobiologically motivated. This learning rule combines features of unsupervised (Hebbian) and supervised (reinforcement) learning and is stochastic with respect to the selection of the time points when a synapse is modified. Moreover, the learning rule does not only affect the synapse between pre- and postsynaptic neuron, which is called homosynaptic plasticity, but effects also further remote synapses of the pre- and postsynaptic neuron. This more complex form of synaptic plasticity has recently come under investigations in neurobiology and is called heterosynaptic plasticity. We demonstrate that this learning rule is useful in training neural networks by learning parity functions including the exclusive-or (XOR) mapping in a multilayer feed-forward network. We find, that our stochastic learning rule works well, even in the presence of noise. Importantly, the mean learning time increases with the number of patterns to be learned polynomially, indicating efficient learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑