arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1407.7906cs.LG
收藏

自动编码器如何通过目标传播在深度网络中提供信用分配

How Auto-Encoders Could Provide Credit Assignment in Deep Networks via Target Propagation

Université de Montréal(蒙特利尔大学)

Yoshua Bengio

摘要:

我们建议利用{ \em重建}作为深度学习的层局部训练信号。重建可以以目标传播的形式传播,其起到类似于反向传播的作用,但有助于减少对导数的依赖,以便在可能的强非线性的许多级别上执行信用分配(这对于反向传播是困难的)。正则化自动编码器倾向于产生作为其输入的更可能版本的重构,即,向更高可能性方向的微小移动。通过概括梯度,目标传播还可以允许训练具有离散隐藏单元的深度网络。如果自动编码器在输入中采用输入和目标(或任何边信息)的表示,则其对输入表示的重构提供了朝向更可能的表示的目标,该表示以所有边信息为条件。深度自动编码器解码路径以学习的方式概括梯度传播,从而不仅可以处理无穷小的变化,而且可以处理更大的离散变化,希望允许通过非线性操作的长链进行信用分配。除了每一层都是一个很好的自动编码器之外,编码器还学会了通过将数据转换到一个更容易建模的空间,扁平化流形和解开因子来取悦上层。这种方法的动机和理论的理由是在本文中,连同将不得不被数学或实验验证,包括一个假设,说明这种自动编码器介导的目标传播可以在大脑中发挥的作用,信用分配通过许多非线性,噪声和离散的转换。

英文摘要:

We propose to exploit {\em reconstruction} as a layer-local training signal for deep learning. Reconstructions can be propagated in a form of target propagation playing a role similar to back-propagation but helping to reduce the reliance on derivatives in order to perform credit assignment across many levels of possibly strong non-linearities (which is difficult for back-propagation). A regularized auto-encoder tends produce a reconstruction that is a more likely version of its input, i.e., a small move in the direction of higher likelihood. By generalizing gradients, target propagation may also allow to train deep networks with discrete hidden units. If the auto-encoder takes both a representation of input and target (or of any side information) in input, then its reconstruction of input representation provides a target towards a representation that is more likely, conditioned on all the side information. A deep auto-encoder decoding path generalizes gradient propagation in a learned way that can could thus handle not just infinitesimal changes but larger, discrete changes, hopefully allowing credit assignment through a long chain of non-linear operations. In addition to each layer being a good auto-encoder, the encoder also learns to please the upper layers by transforming the data into a space where it is easier to model by them, flattening manifolds and disentangling factors. The motivations and theoretical justifications for this approach are laid down in this paper, along with conjectures that will have to be verified either mathematically or experimentally, including a hypothesis stating that such auto-encoder mediated target propagation could play in brains the role of credit assignment through many non-linear, noisy and discrete transformations.

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。

↑