In conventional backprop, error signals lead to adjustments in the synapses, which in turn cause changes in neuronal activity.

在传统的反向传播中， 误差信号会导致突触的调整，进而引起神经元活动的变化。

This error signal moves backwards through the network, layer by layer, strengthening or weakening each connection in order to minimise any future errors.

该错误信号在网络中逐层向后移动，加强或削弱每个连接， 以尽量减少未来的错误。

If the network is shown an image of a bird but mistakenly concludes that it is not, then—once it realises the gaffe—it generates an error signal.

如果向网络展示一张鸟的图像， 但错误地认为它不是鸟，那么一旦它意识到失误， 它就会生成错误信号。

For backpropagation to work in the brain, a perfect mirror image of each network of neurons would therefore have to exist in order to send the error signal backwards.

为了使反向传播在大脑中发挥作用，每个神经元网络必须存在一个完美的镜像，以便将错误信号向后发送。

If artificial neural networks can be given biologically realistic features, such as specialised neurons that can integrate activity and error signals in different parts of the cell, then backprop can occur with a single set of neurons.

如果人工神经网络能够具备生物学上的真实特征，比如能够整合细胞不同部分的活动和错误信号的专门神经元，那么反向传播就可以用一组神经元进行。