Disclaimer: I’ll be briefly mentioning logistic-regression and basic feed-forward neural networks, so its helpful to have programmed with those 2 models before reading this piece.

免责声明：我将简要介绍逻辑回归和基本前馈神经网络，因此在阅读本文之前使用这两种模型进行编程将很有帮助。

OK — before machine learning folks come running after me after reading the title, I’m not talking about linear regression, for example. Yes, in linear regression, you can use the R-squared (or adjusted R-squared statistic) to talk about explained variance, and since linear regression only involves addition between independent variables (or predictors), they’re pretty interpretable. If you were doing a linear regression to predict, say the price of a car Car_Price, based on the number of seats, mileage, maximum-speed, and battery life, your linear model could be –– say Car_Price = c1*Seats + c2*Mileage + c3*Speed + c4*Battery_Power –– the fact that variables are only added makes it pretty interpretable. But when it comes to more complex prediction models like Logistic Regression and neural networks, everything about the predictors (or called “features” in ML) becomes more confusing. And logistic-regression & neural networks fall under supervised learning, because they basically just estimate a complicated black-box function from data -> labels.

好吧-例如，在机器学习的人们在阅读标题后追赶我之前，我不是在谈论线性回归。 是的，在线性回归中，您可以使用R平方(或调整后的R平方统计量)来讨论已解释的方差，并且由于线性回归仅涉及自变量(或预测变量)之间的加法，因此它们是可以解释的。 如果您要进行线性回归以预测汽车的价格，例如Car_Price ，基于座位数，里程，最大速度和电池寿命，则您的线性模型可能为-说Car_Price = c1 * 座位 + c2 * 里程 + c3 * 速度 + c4 * Battery_Power –仅添加变量的事实使其易于解释。 但是，当涉及到诸如Logistic回归和神经网络之类的更复杂的预测模型时，关于预测变量的一切(在ML中称为“功能”)都会变得更加混乱。 逻辑回归和神经网络属于监督学习 ，因为它们基本上只是从数据->标签估计复杂的黑盒功能。

People use logistic regression to predict whether something is true or not; for example, if patient X has a disease or not. It’s an example of a nonlinear classifier, because instead of just adding the features together, the features are mapped through the nonlinear sigmoid function, which squishes all inputs into the range between 0 and 1, since logistic regression is supposed to represent a probability. (Technically, if you search logistic-regression on Wikipedia, the “decision boundary” is linear, but that’s not the point.) TO me at least, logistic-regression already seems a bit less interpretable than linear-regression because of the nonlinear part. And neural networks are logistic regression chained together! (It’s a rough analogy, but it helps explain a point.) Neural nets, are by definition, made to be nonlinear so it would find non-linear connections between features and be a better predictor for say, image recognition –– why? Because the pixels are considered features, and the pixels making up a recognizable image are related in a non-linear way since images are complex.

人们使用逻辑回归来预测某些事物是否正确。 例如，患者X是否患有疾病。 这是一个非线性分类器的示例，因为通过非线性Sigmoid函数映射了这些特征，而不是仅将特征加在一起，该函数将所有输入压缩在0到1之间的范围内，因为逻辑回归应该表示概率。 (从技术上讲，如果您在Wikipedia上搜索逻辑回归，则“决策边界”是线性的，但这不是重点。)至少对我而言，由于非线性部分，逻辑回归似乎比线性回归的解释性差一些。 而且神经网络是逻辑回归链接在一起的！ (这是一个粗略的类比，但它有助于解释一个观点。)根据定义，神经网络是非线性的，因此可以发现特征之间的非线性联系，并且可以更好地预测图像识别，这是为什么？ 因为像素被认为是特征，并且由于图像复杂，所以构成可识别图像的像素以非线性方式相关。

But neural networks are often described as an unexplainable black box, and you do NOT want a neural network making important decisions about employment, loans, health-data, and so on if you can’t explain the reasons for the model’s decision. And given at least a. few self-driving fatal car accidents whose software runs on deep learning, a neural network’s decisions that led to a injury or death can’t even be explained in a principled way!

但是神经网络通常被描述为无法解释的黑匣子 ，如果您无法解释模型决策的原因，则您不希望神经网络对就业，贷款，健康数据等做出重要决策。 并至少给定一个。 很少有软件能够在深度学习上运行的自动驾驶致命车祸 ，甚至无法用原则性的方式来解释导致受伤或死亡的神经网络决策！

Neural networks are based on the idea of approximating functions, or mappings, between data and its label (example: image of a cat, cat-label). But in the 1989 original paper proving that neural networks can do this, the author, Cybenko, stated at the end: “At this point, we can only say that the majority of [mapping/function] approximation problems will require astronomical numbers of terms [neural nodes].” So while neural networks can create any function mapping between, say images (or predicting the next-word, with recurrent nets), they often have to have hundreds-of-thousands to millions of parameters (also called “weights”, same as “terms” that Cybenko says), with no principled way of interpreting and explaining the nonlinear connections. And human brains don’t need to see thousands of examples to generalize as neural nets do. For example, AlexNet, a famous neural network trained to classify cats, houses, cars, and real-life objects, has 60 million parameters, and had to be trained on 15 million images with almost 700 images for each label. And it sucked up an immense computational energy with multiple GPUs –– technologies that mostly large companies and research groups with tons of money have access to.

神经网络基于在数据及其标签(例如：猫的图像，猫标签)之间近似函数或映射的想法。 但是在1989年证明神经网络可以做到这一点的原始论文中 ，作者Cybenko最后说：“ 在这一点上，我们只能说大多数[映射/函数]逼近问题将需要天文数字的项[神经节点] 。” 因此，尽管神经网络可以在图像之间(或使用递归网络预测下一词)之间创建任何函数映射，但它们通常必须具有数十万至数百万个参数(也称为“权重”，与Cybenko所说的“术语”，没有解释和解释非线性连接的原则方法。 人类的大脑不需要像神经网络那样去看成千上万个例子来进行概括。 例如，著名的神经网络AlexNet受过训练，可以对猫，房屋，汽车和现实物体进行分类，它具有6000万个参数，并且必须针对1500 万幅图像进行训练，每个标签将近700张图像。 而且它利用多个 GPU吸收了巨大的计算能力-大多数拥有大量资金的大型公司和研究小组都可以使用的技术。

Personally, I believe that AI could use a dose of two things to make itself interpretable: inference, and unsupervised learning. Why? Well, I believe it comes down to the following equation:

我个人认为AI可以使用两件事来使自己具有可解释性： 推理和无监督学习 。 为什么？ 好吧，我相信可以归结为以下等式：

This is Bayes’ Theorem, but with 2 hypothesis. Basically it says that the belief we give to hypothesis 1 over hypothesis 2 after seeing data, is just the product of how likely the data is assuming our hypotheses, times what we thought about the hypotheses before seeing the data. There’s evidence our brain computes probabilistic inference subconsciously in a similar way. But where does unsupervised learning play in, you say? Well, precisely in the “likelihood” piece of the equation. If you’ve heard of unsupervised learning related to “clustering”, or “finding patters in data without labels” –– that’s all true. But unsupervised learning is fundamentally about density-estimation, a fancy of way of saying “data description”. Density estimation gives us more power than just clustering. It can generate new data all on its own! And crucially, if we can use it to generate new data, then assuming either hypothesis, we can compare the distribution of generated data, to what we see in our test data. And if the test data is more likely to be generated with our estimated density by assuming Hypothesis 1 over 2, we can decide to choose one over the other. That kind of decision, I believe at least, is explainable and understandable because human brains are already wired to understand likelihood and reason with uncertainty. Generating new data in our mind is an important part of human intelligence –– so it should definitely be a key part of Interpretable-AI.

这是贝叶斯定理，但有两个假设。 基本上说，看到数据后我们对假设1相对于假设2的信念，仅仅是数据假设我们的假设的可能性乘以我们在看到数据之前对假设的想法的乘积。 有证据表明， 我们的大脑以类似的方式下意识地计算了概率推论 。 但是，您说无监督学习在哪里发挥作用？ 好吧，正好在等式的“ 可能性”部分。 如果您听说过与“聚类”或“在没有标签的情况下寻找模式”有关的无监督学习，那是完全正确的。 但是无监督学习从根本上讲是关于密度估计的 ，这是一种表达“数据描述”的方式。 密度估算不仅提供聚类功能，还为我们提供了更多功能。 它可以自行生成新数据！ 至关重要的是，如果我们可以使用它来生成新数据，则假设有任何一种假设，我们都可以将生成数据的分布与测试数据中看到的进行比较。 如果假设1比2假设更可能以我们的估计密度生成测试数据，则我们可以决定选择一个。 至少，我认为这种决定是可以解释和理解的，因为人脑已经连接起来，以不确定性理解可能性和原因。 在我们脑海中生成新数据是人类智能的重要组成部分–因此，它绝对应该是Interpretable-AI的关键部分。

In my next article, I’ll be going over a use case of this. I’ll be analyzing the “Hepatocellular Carcinoma” dataset from the free online UCI Learning Repository , and show the code and results for classifying whether a patient with certain medical features survives or dies from the carcinoma. We’ll get to see differences in interpretability using 1) logistic-regression model to predict survival, and 2) a unsupervised, generative model, like above, to predict survival. See you then!

在我的下一篇文章中，我将介绍这个用例。 我将分析免费的在线UCI学习资料库中的“肝细胞癌”数据集 ，并显示用于对具有某些医学特征的患者存活还是死于癌症进行分类的代码和结果。 我们将使用1)逻辑回归模型预测生存率，以及2)无监督的生成模型(如上)预测生存率来了解可解释性的差异。 回头见！

EDIT: My follow-up article, “Interpretable-AI: Use-Case with Health Data” is out on my Medium profile now! Any readers here who finished this piece, feel free to check it out!

编辑：我的后续文章“ Interpretable-AI：具有健康数据的用例 ”现在在我的Medium个人资料中！ 这里的所有读者只要完成这篇文章，就可以随时查看！

Feel free to contact me at my LinkedIn!

请随时通过我的LinkedIn与我联系！