发电机网络的交替反向传播算法
Alternating Back-Propagation for Generator Network
摘要：
本文提出了一种用于发电机网络模型学习的交替反向传播算法。该模型是因子分析的非线性推广。在这个模型中，从连续的潜在因素到观察到的信号的映射由卷积神经网络参数化。交替反向传播算法迭代以下两个步骤：（1）推理反向传播，其通过朗之万动力学或梯度下降来推断潜在因子。(2)学习反向传播，它通过梯度下降来更新给定推断的潜在因素的参数。这两个步骤中的梯度计算都是由反向传播提供动力的，并且它们共享大部分共同的代码。我们表明，交替反向传播算法可以学习现实的自然图像，视频序列和声音的生成器模型。此外，它还可以用于从不完整或间接的训练数据中学习。
英文摘要：
This paper proposes an alternating back-propagation algorithm for learning the generator network model. The model is a non-linear generalization of factor analysis. In this model, the mapping from the continuous latent factors to the observed signal is parametrized by a convolutional neural network. The alternating back-propagation algorithm iterates the following two steps: (1) Inferential back-propagation, which infers the latent factors by Langevin dynamics or gradient descent. (2) Learning back-propagation, which updates the parameters given the inferred latent factors by gradient descent. The gradient computations in both steps are powered by back-propagation, and they share most of their code in common. We show that the alternating back-propagation algorithm can learn realistic generator models of natural images, video sequences, and sounds. Moreover, it can also be used to learn from incomplete or indirect training data.
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。
