我想在神经网络术语的背景下:

Epoch:当你的网络最终遍历整个训练集(即，每个训练实例一次)时，它完成了一个Epoch。

为了定义迭代(也就是步骤)，你首先需要知道批处理的大小:

Batch Size: You probably wouldn't like to process the entire training instances all at one forward pass as it is inefficient and needs a huge deal of memory. So what is commonly done is splitting up training instances into subsets (i.e., batches), performing one pass over the selected subset (i.e., batch), and then optimizing the network through backpropagation. The number of training instances within a subset (i.e., batch) is called batch_size. Iteration: (a.k.a training steps) You know that your network has to go over all training instances in one pass in order to complete one epoch. But wait! when you are splitting up your training instances into batches, that means you can only process one batch (a subset of training instances) in one forward pass, so what about the other batches? This is where the term Iteration comes into play: Definition: The number of forwarding passes (The number of batches that you have created) that your network has to do in order to complete one epoch (i.e., going over all training instances) is called Iteration.

例如，当你有10,000个训练实例，你想用10的大小进行批处理;你必须进行10,000/10 = 1,000次迭代才能完成1个epoch。

希望这能回答你的问题!

我想在神经网络术语的背景下:

Epoch:当你的网络最终遍历整个训练集(即，每个训练实例一次)时，它完成了一个Epoch。

为了定义迭代(也就是步骤)，你首先需要知道批处理的大小:

Batch Size: You probably wouldn't like to process the entire training instances all at one forward pass as it is inefficient and needs a huge deal of memory. So what is commonly done is splitting up training instances into subsets (i.e., batches), performing one pass over the selected subset (i.e., batch), and then optimizing the network through backpropagation. The number of training instances within a subset (i.e., batch) is called batch_size. Iteration: (a.k.a training steps) You know that your network has to go over all training instances in one pass in order to complete one epoch. But wait! when you are splitting up your training instances into batches, that means you can only process one batch (a subset of training instances) in one forward pass, so what about the other batches? This is where the term Iteration comes into play: Definition: The number of forwarding passes (The number of batches that you have created) that your network has to do in order to complete one epoch (i.e., going over all training instances) is called Iteration.

例如，当你有10,000个训练实例，你想用10的大小进行批处理;你必须进行10,000/10 = 1,000次迭代才能完成1个epoch。

希望这能回答你的问题!

要理解它们之间的区别，你必须理解梯度下降算法及其变体。

在我开始回答这个问题之前，我想先了解一下背景。

批处理是完整的数据集。它的大小是可用数据集中训练示例的总数。

小批量大小是学习算法在单次传递(向前和向后)中处理的示例数量。

迷你批是给定迷你批大小的数据集的一小部分。

迭代是算法已经看到的数据批次的数量(或者简单地说，算法已经在数据集上完成的次数)。

epoch是一个学习算法看到完整数据集的次数。现在，这可能不等于迭代的次数，因为数据集也可以小批量处理，本质上，一次传递可能只处理数据集的一部分。在这种情况下，迭代的数量不等于epoch的数量。

在批处理梯度下降的情况下，整个批处理在每个训练通过。因此，梯度下降优化器的收敛比Mini-batch梯度下降更平滑，但需要更多的时间。如果存在最优条件，分批梯度下降法保证能找到最优条件。

随机梯度下降是小批量梯度下降的一种特殊情况，其中小批量大小为1。

在神经网络术语中:

一个epoch =所有训练示例的一个向前传递和一个向后传递 批大小=一次向前/向后传递中训练示例的数量。批处理大小越大，所需的内存空间就越大。 迭代次数=通过次数，每次通过使用[批大小]示例的数量。需要明确的是，一次传球=一次向前传球+一次向后传球(我们不把向前传球和向后传球算作两次不同的传球)。

例如:如果你有1000个训练样本，你的批处理大小是500，那么将需要2次迭代来完成1个epoch。

供参考:权衡批大小和迭代次数来训练神经网络

术语“批处理”是模棱两可的:有些人用它来表示整个训练集，有些人用它来指代一次向前/向后传递中的训练示例的数量(就像我在这个回答中所做的那样)。为了避免这种歧义，并明确batch对应于一次正向/向后传递中训练示例的数量，可以使用术语mini-batch。

许多神经网络训练算法都涉及到将整个数据集多次呈现给神经网络。通常，整个数据集的单一表示被称为“epoch”。相比之下，一些算法一次只向神经网络提供一个案例的数据。

“迭代”是一个更一般的术语，但既然你和“epoch”一起问了这个词，我假设你的来源是指一个单一案例对神经网络的呈现。

一个epoch包含几个迭代。这就是这个时代。让我们把epoch定义为训练神经网络时在数据集上的迭代次数。