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 1612.03214cs.LGcs.NEq-bio.NC
收藏

在具有对比赫布可塑性的基于能量的模型中使用尖峰神经元进行深度学习

Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity

École Normale Supérieure(巴黎高等师范学院)

Thomas Mesnard, Wulfram Gerstner, Johanni Brea

摘要:

在机器学习中,多层神经网络(深度学习)中的误差反向传播在监督和强化学习任务中取得了令人印象深刻的成功。然而,作为大脑学习的模型,深度学习一直被认为是不可信的,因为它的基本形式依赖于非局部可塑性规则。为了克服这个问题,提出了基于能量的局部对比赫布学习模型,并在一个分类任务与率神经元网络进行了测试。我们扩展了这项工作,通过实现和测试这样一个模型与泄漏集成和火灾神经元网络。初步结果表明,它是可能的学习一个非线性回归任务与隐藏层,尖峰神经元和局部突触可塑性规则。

英文摘要:

In machine learning, error back-propagation in multi-layer neural networks (deep learning) has been impressively successful in supervised and reinforcement learning tasks. As a model for learning in the brain, however, deep learning has long been regarded as implausible, since it relies in its basic form on a non-local plasticity rule. To overcome this problem, energy-based models with local contrastive Hebbian learning were proposed and tested on a classification task with networks of rate neurons. We extended this work by implementing and testing such a model with networks of leaky integrate-and-fire neurons. Preliminary results indicate that it is possible to learn a non-linear regression task with hidden layers, spiking neurons and a local synaptic plasticity rule.

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。

↑