DCIGN

        Deep convolutional inverse graphics networks (DCIGN) have a somewhat misleading name, as they are actually VAEs but with CNNs and DNNs for the respective encoders and decoders. These networks attempt to model “features” in the encoding as probabilities, so that it can learn to produce a picture with a cat and a dog together, having only ever seen one of the two in separate pictures. Similarly, you could feed it a picture of a cat with your neighbours’ annoying dog on it, and ask it to remove the dog, without ever having done such an operation. Demo’s have shown that these networks can also learn to model complex transformations on images, such as changing the source of light or the rotation of a 3D object. These networks tend to be trained with back-propagation.

        深度卷积逆图形网络(DCIGN)有一个有点误导人的名字，因为它们实际上是VAEs，但是分别用于编码器和解码器的是CNNs和DNNs。这些网络试图将编码中的“特征”建模为概率，这样它就能学会在只在单独的图片中看到一只猫和一只狗的情况下，同时生成一张猫和狗的图片。

      同样，你也可以给它喂一张猫的照片，上面有你邻居那只讨厌的狗，然后让它把狗移走，而不用做这样的手术。演示表明，这些网络还可以学习对图像进行复杂的转换建模，比如改变光源或3D对象的旋转。这些网络往往经过反向传播训练。

Kulkarni, Tejas D., et al. “Deep convolutional inverse graphics network.” Advances in Neural Information Processing Systems. 2015.

GAN

      Generative adversarial networks (GAN) are from a different breed of networks, they are twins: two networks working together. GANs consist of any two networks (although often a combination of FFs and CNNs), with one tasked to generate content and the other has to judge content. The discriminating network receives either training data or generated content from the generative network. How well the discriminating network was able to correctly predict the data source is then used as part of the error for the generating network. This creates a form of competition where the discriminator is getting better at distinguishing real data from generated data and the generator is learning to become less predictable to the discriminator. This works well in part because even quite complex noise-like patterns are eventually predictable but generated content similar in features to the input data is harder to learn to distinguish. GANs can be quite difficult to train, as you don’t just have to train two networks (either of which can pose it’s own problems) but their dynamics need to be balanced as well. If prediction or generation becomes to good compared to the other, a GAN won’t converge as there is intrinsic divergence.

      生成对抗网络(GAN)来自不同种类的网络，它们是双胞胎:两个网络一起工作。GANs由任意两个网络组成(尽管通常是ff和CNNs的组合)，一个负责生成内容，另一个负责判断内容。识别网络从生成网络接收训练数据或生成内容。然后将判别网络对数据源的正确预测程度作为生成网络误差的一部分。这就形成了一种竞争形式，在这种竞争中，甄别者越来越善于区分真实数据和生成的数据，而生成者正在学习如何让甄别者变得更难以预测。这在一定程度上很有效，因为即使是非常复杂的类似于噪音的模式，最终也是可以预测的，但生成的内容在特性上与输入数据相似，这一点更难区分。

      GANs可能很难训练，因为您不仅需要训练两个网络(其中任何一个都可能带来它自己的问题)，而且还需要平衡它们的动态。如果预测或生成变得比另一个好，GAN将不会收敛，因为有内在的发散。

Goodfellow, Ian, et al. “Generative adversarial nets.” Advances in Neural Information Processing Systems (2014).

Original Paper PDF

LSM

     Liquid state machines (LSM) are similar soups, looking a lot like ESNs. The real difference is that LSMs are a type of spiking neural networks: sigmoid activations are replaced with threshold functions and each neuron is also an accumulating memory cell. So when updating a neuron, the value is not set to the sum of the neighbours, but rather added to itself. Once the threshold is reached, it releases its’ energy to other neurons. This creates a spiking like pattern, where nothing happens for a while until a threshold is suddenly reached.

     液态机器(LSM)是类似的soups，看起来很像ESNs。真正的不同之处在于，LSMs是一种尖峰型神经网络:sigmoid激活被阈值函数取代，每个神经元也是一个累积的记忆细胞。因此，当更新一个神经元时，该值不会被设置为相邻神经元的和，而是被添加到它自己。一旦达到这个阈值，它就会向其他神经元释放能量。这就创建了一个类似于spiking的模式，在此模式中，一段时间内什么都没有发生，直到突然达到一个阈值。

Maass, Wolfgang, Thomas Natschläger, and Henry Markram. “Real-time computing without stable states: A new framework for neural computation based on perturbations.” Neural computation 14.11 (2002): 2531-2560.

Original Paper PDF