BACKPROPAGATION - 翻译成中文

• 反向传播

在 英语 中使用 Backpropagation 的示例及其翻译为 中文

However, I think it's useful to understand the concepts of Perceptron, Multi-Layer Perceptron, and the Backpropagation algorithm.
但是，我认为了解Perceptron，Multi-LayerPerceptron和Backpropagation算法的概念对神经网络的学习是很有用的。

This is because backpropagation through discrete variables is generally not possible, making the model difficult to train efficiently.
这是因为通过离散变量的反向传播通常是不可能的，使得模型难以有效地训练。

The solution, independently derived by multiple groups, is backpropagation through time.
解决办法是，通过多重群组独立推导，通过时间进行反向传播。

Describe the various terms related to neural networks, such as“activation”,“backpropagation” and“feedforward”.
描述与类神经网络相关的各种术语，例如“activation”，“backpropagation”和“feedforward”.

Another possible mechanism, by which biological neural networks could approximate backpropagation, is“feedback alignment”(Lillicrap et al., 2014; Liao et al., 2015).
生物神经网络可以近似反向传播的另一种可能机制是“反馈比对”（feedbackalignment）（Lillicrapetal.,2014;Liaoetal.,2015）。

These striking successes have primarily been based on the backpropagation and dropout algorithms, using piecewise linear units[18-20] which have a particularly well-behaved gradient.
这些惊人的成功主要基于反向传播和dropout算法，使用分段线性单元[17，8，9]，具有特别表现良好的梯度。

The motivation for backpropagation is to train a multi-layered neural network such that it can learn the appropriate internal representations to allow it to learn any arbitrary mapping of input to output.
反向传播算法的发展的目标和动机是找到一种训练的多层神经网络的方法，于是它可以学习合适的内部表达来让它学习任意的输入到输出的映射。

The answer: through backpropagation.
答案是：通过反向传播。

Backpropagation refers to two things.
反向传播是指两件事情：.

Data normalization is used during backpropagation.
在反向传播期间要使用数据标准化。

Backpropagation- What neural networks use.
反向传播-神经网络使用什么。

The four fundamental equations behind backpropagation.
反向传播背后的四个基本等式.

Users can train the network through backpropagation.
用户可以通过反向传播训练该网络。

The convergence in backpropagation learning is not guaranteed.
在反向传播学习的收敛性不能保证。

Unfortunately, this makes backpropagation computation difficult.
很遗憾，这会导致反向传播算法的计算变得困难。

Updating the weights and biases, known as backpropagation.
更新权重和偏置，称为反向传播.

Now this architecture can be jointly trained using backpropagation.
现在这个架构可以使用反向传播（backpropagation）联合训练。

The concept, called backpropagation, is fairly simple.
这个概念称为反向传播，相当简单。

Geoffrey Hinton already believes we should rethink backpropagation.
GeoffreyHinton认为我们应该重新考虑反向传播。

This is called Backpropagation Through Time(BPTT).
我们将该过程称为随时间反向传播(BPTT)。