arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1102.0166q-bio.NCnlin.AO
收藏

循环联系的Hebbian学习:几何学观点

Hebbian learning of recurrent connections: a geometrical perspective

Mathieu N. Galtier, Olivier D. Faugeras, Paul C. Bressloff

摘要:

我们展示了一个具有可修改的经常性连接的Hopfield网络如何通过缓慢的Hebbian学习来提取输入空间的底层几何。首先,我们使用一个慢/快的分析,以获得一个平均的系统,其动态来自能量函数,因此总是收敛到平衡点。平衡反映了输入的相关结构,一个全局对象只通过局部经常性的相互作用提取。其次,我们使用数值方法来说明学习如何提取输入的隐藏几何结构。事实上,多维缩放方法可以将最终的连接矩阵投影到高维空间中的距离矩阵上,神经元在该空间中的空间位置被标记。由此产生的网络结构大致是卷积的。投影的残差定义了在该过程中最小化的连接的非卷积部分。最后,我们展示了如何限制神经元生活的空间的尺寸产生类似于皮层地图的模式。我们激励这使用基于线长最小化的能源效率参数。最后,我们展示了这种方法是如何导致初级视觉皮层中眼优势或方向列的出现的。此外,我们还确定了非卷积(或长距离)连接是不完整的,并且在方向学习的情况下是共同对齐的。

英文摘要:

We show how a Hopfield network with modifiable recurrent connections undergoing slow Hebbian learning can extract the underlying geometry of an input space. First, we use a slow/fast analysis to derive an averaged system whose dynamics derives from an energy function and therefore always converges to equilibrium points. The equilibria reflect the correlation structure of the inputs, a global object extracted through local recurrent interactions only. Second, we use numerical methods to illustrate how learning extracts the hidden geometrical structure of the inputs. Indeed, multidimensional scaling methods make it possible to project the final connectivity matrix on to a distance matrix in a high-dimensional space, with the neurons labelled by spatial position within this space. The resulting network structure turns out to be roughly convolutional. The residual of the projection defines the non-convolutional part of the connectivity which is minimized in the process. Finally, we show how restricting the dimension of the space where the neurons live gives rise to patterns similar to cortical maps. We motivate this using an energy efficiency argument based on wire length minimization. Finally, we show how this approach leads to the emergence of ocular dominance or orientation columns in primary visual cortex. In addition, we establish that the non-convolutional (or long-range) connectivity is patchy, and is co-aligned in the case of orientation 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。

↑