机器学习与分布式机器学习_机器学习的歧义

机器学习与分布式机器学习

超越最高精度 (Beyond Achieving Top Accuracy)

We are familiar with the idea of using machine learning to make predictions and inferences to high accuracies. This is after all a big part of what machine learning is expected to do.

我们熟悉使用机器学习对高精度进行预测和推断的想法。 毕竟，这是机器学习所期望做的很大一部分。

Interestingly and importantly, we can leverage further on machine learning models. Beyond using the model to make top accuracy predictions, we can use it to create Uncertainty, Ambiguity or even Contention.

有趣且重要的是，我们可以进一步利用机器学习模型。 除了使用模型做出最高的准确性预测外，我们还可以使用它来创建不确定性，歧义甚至竞争。

我们不喜欢清晰和确定性吗？ (Don’t We Like Clarity and Certainty?)

Not all the time. For good motivations,

并非一直如此。 为了好的动力

• Testers may want to create examples that are uncertain, so we can stress test a system for its result or even its decision on borderline inputs.
  测试人员可能想创建不确定的示例，因此我们可以对系统的结果甚至是对边界输入的决策进行压力测试。
• Designers may be interested to visualise a hybrid prototype that combines existing products, but which we do not have a definite specification right now.
  设计人员可能想对结合了现有产品的混合原型进行可视化，但是我们目前尚无明确的规格。
• Trainers may want to create content that is ambiguous so that there are no straightforward answers, which therefore encourage participants to engage in debate.
  培训人员可能希望创建含糊不清的内容，以便没有简单的答案，因此鼓励参与者进行辩论。

The applications are plentiful.

应用程序很多。

真实的例子 (Real Example)

Let us use the MNIST dataset that contains images of the ten digits from 0 to 9. We then train a model to at least 98% accuracy, that is, a model that correctly predicts images to their corresponding digits at least 98% of the time.

让我们使用包含从0到9的十个数字的图像的MNIST数据集。然后，我们训练一个模型至少达到98％的准确度，即，一个模型至少在98％的时间内正确地将图像预测为其对应的数字。

Instead of stopping here, we further leverage on the model — we use the model to apply ambiguity to the digits.

除了在这里止步不前，我们进一步利用模型- 我们使用模型对数字应用歧义。

Let us confuse the digit “3” with “8”.

让我们将数字“ 3”与“ 8”混淆。

The machine learning model filled in the blanks. It dotted two spots on the left of 3. Now, it is not unreasonable for a person to contend this 3 as an 8.

机器学习模型填补了空白。 它在3的左侧点了两个点。现在，一个人将3视为8并不是不合理的。

Let us confuse the digit “4” with “9”.

让我们将数字“ 4”与“ 9”混淆。

The model attempted to build a roof over the 4 to make it closer to a 9. The model is conscious not to complete the entire roof as its goal is to make the digit uncertain between 4 and 9.

该模型试图在4上建立屋顶以使其更接近9。该模型有意识地不完成整个屋顶，因为它的目标是使数字在4到9之间不确定。

Let us confuse the digit “6” with “5”.

让我们将数字“ 6”与“ 5”混淆。

The model cut 6 in the middle and pulled out the resulting loose end to create the hook in 5. Additionally, it sketched a short stroke at the top of 6 to make it look like 5. It is now uncertain if the digit is 6 or 5.

模型在中间切出6，然后拉出产生的松动端，以在5中创建钩子。此外，它还在6的顶部绘制了短笔画以使其看起来像5。现在不确定数字是6还是5。 5，

模型是如何做到的？ (How does the Model Do It?)

By training the model to an accuracy of 98%, it has understood what digit images should look like. We could then ask it to engineer its knowledge and show us how digits that are uncertain, ambiguous or contentious look like.

通过将模型训练到98％的准确度，它已经了解了数字图像的外观。 然后，我们可以要求它设计知识，并向我们展示不确定，模棱两可或有争议的数字。

For example, it is akin to asking “Could you create something that is in between “5” and “6” since you already know how they individually look like?”

例如，这类似于询问“您是否可以创建介于“ 5”和“ 6”之间的内容，因为您已经知道它们的外观？”

最后的想法 (Last Thoughts)

There are many good motivations for creating uncertainty, ambiguity or even contention, some of which have been explained above. Almost surely, there are also ways that uncertainty, ambiguity and contention can be used to harm or exploit! The following question probably gives us a better appreciation — could uncertain data be used as an attack against my automated system and cause it to produce an undesired decision?

产生不确定性，歧义甚至争执的动机很多，上面已经解释了其中的一些动机。 几乎可以肯定，不确定性，模糊性和争用还可以通过其他方式来损害或利用！ 以下问题可能会给我们带来更好的理解-不确定的数据是否可以用作对我的自动化系统的攻击，并导致产生不希望的决策？

翻译自: https://medium.com/@ryyr/machine-learning-for-ambiguity-dbb99db613af

机器学习与分布式机器学习