tensorflow自编码_去噪自动编码器— Tensorflow

tensorflow自编码

什么是自动编码器？ (What are Autoencoders?)

Autoencoders are an unsupervised learning technique in which we leverage neural networks for the task of representation learning. Specifically, we’ll design a neural network architecture such that we impose a bottleneck in the network which forces a compressed knowledge representation of the original input.

自动编码器是一种无监督的学习技术，其中我们利用神经网络来完成表示学习的任务。 具体来说，我们将设计一种神经网络体系结构，以使我们在网络中施加一个瓶颈，从而迫使 原始输入的知识知识 压缩 。

The ideal autoencoder model balances the following:

理想的自动编码器模型在以下方面取得了平衡：

• Sensitive to the inputs enough to accurately build a reconstruction.
  对输入足够敏感，可以准确地进行重建。
• Insensitive enough to the inputs that the model doesn’t simply memorize or overfit the training data.
  对输入足够不敏感，模型无法简单地记住或过度拟合训练数据。

We’d like our autoencoder to be sensitive enough to recreate the original observation but insensitive enough to the training data such that the model learns a generalizable encoding and decoding.

我们希望我们的自动编码器足够灵敏以重新创建原始观测值，但又对训练数据不灵敏，从而使模型学习通用的编码和解码。

去噪自动编码器背后的想法 (The idea behind Denoising Autoencoder)

One approach towards developing a generalizable model is to slightly corrupt the input data but still, maintain the uncorrupted data as our target output.

开发通用模型的一种方法是稍微破坏输入数据，但仍然将未破坏的数据作为我们的目标输出。

With this approach, our model isn’t able to simply develop a mapping which memorizes the training data because our input and target output are no longer the same. Rather, the model learns a vector field for mapping the input data towards a lower-dimensional manifold (A manifold describes the high-density region where the input data concentrates); if this manifold accurately describes the natural data, we’ve effectively “canceled out” the added noise.

使用这种方法， 我们的模型不能简单地开发一个用于存储训练数据的映射，因为我们的输入和目标输出不再相同 。 相反，模型学习一个向量场，用于将输入数据映射到低维流形(流形描述了输入数据集中的高密度区域)； 如果此歧管准确地描述了自然数据，则我们可以有效地“消除”所增加的噪声。

The above figure visualizes the vector field described by comparing the reconstruction of xx with the original value of xx. The yellow points represent training examples prior to the addition of noise. As you can see, t