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 1703.07943q-bio.NCcond-mat.dis-nncond-mat.stat-mechcs.LGcs.NE
收藏

零突触在无监督特征学习中的作用

Role of zero synapses in unsupervised feature learning

RIKEN Brain Science Institute(理化学研究所脑科学中心)

Haiping Huang

摘要:

真实神经回路中的突触可以取离散值,包括零(沉默或潜在)突触。零突触在无标记噪声数据的无监督特征学习中的计算作用尚不清楚,因此理解突触活动的稀疏性在学习过程中如何形成及其与感受野形成的关系是重要的。在这里,我们通过统计力学方法来制定这种稀疏特征学习。我们发现学习减少了零突触的比例,当该比例在临界数据大小附近迅速减少时,内在结构的感受野开始发展。进一步增加数据大小可以细化感受野,而零突触的一小部分仍然充当轮廓检测器。这种现象不仅在学习手写数字数据集时被发现,而且在学习自然电影刺激实验中测量的视网膜神经活动时也被发现。

英文摘要:

Synapses in real neural circuits can take discrete values, including zero (silent or potential) synapses. The computational role of zero synapses in unsupervised feature learning of unlabeled noisy data is still unclear, thus it is important to understand how the sparseness of synaptic activity is shaped during learning and its relationship with receptive field formation. Here, we formulate this kind of sparse feature learning by a statistical mechanics approach. We find that learning decreases the fraction of zero synapses, and when the fraction decreases rapidly around a critical data size, an intrinsically structured receptive field starts to develop. Further increasing the data size refines the receptive field, while a very small fraction of zero synapses remain to act as contour detectors. This phenomenon is discovered not only in learning a handwritten digits dataset, but also in learning retinal neural activity measured in a natural-movie-stimuli experiment.

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。

↑