Hacker News Reader

Comment by lottin | Hacker News Reader

Inferential statistics is about explaining an observed outcome in terms of its causing factors. Once we have explained it, then we can make predictions. Machine learning skips the explaining part and goes straight to making predictions, without attempting to understand the underlying process that led to the particular outcome. This would be the main difference, in my opinion.

View on HN

Yes, this is my observation as well. Put another way, statistics is primarily concerned with understanding the mechanisms behind something. Predictive power can and will often be sacrificed if it aids explanatory power or conceptual elegance.

By contrast, machine learning is primarily concerned with making the best prediction possible, even if that means sacrificing an understanding of the underlying mechanisms.

The Venn diagram of methods can have a fair degree of overlap.

Neither disposition is right or wrong, but they tend to have natural places where each makes more sense. If you’re trying to predict whether a picture is of a cat or a dog, you probably don’t care much about the constituent contribution of factors to one pictures dogness or catness. On the other hand, if you’re trying to predict traffic collisions based on characteristics of a roadway, you’re probably less concerned with the predicted number of crashes and more concerned with the relative contribution of a handful of independent variables.

If you are trying to predict the failure modes of a cat/dog discriminator on arbitrary images, an understanding of catness/dogness is more useful.

>machine learning skips the explaining part and goes straight to making predictions

what? Then we should call it machine oracle. It uses magic to make the right predictions without any understanding. It's like seeing a strong AI beating the turing test and saying: it was just lucky. I can think only of two possible ways to make right predictions without understanding: luck and cheating. Sure, sometimes ML cheats.

    statistics is about explaining an observed
    outcome in terms of its causing factors.

Isn't it the same for ML? When we train a NN to map input factors to the observed outcome, it will set the weights of the factors that do not influence the outcome to 0.

This is only the case if your model’s features are easy to understand, and one of the motivations for some NN approaches is to avoid having to create your own features.

Causal inference and the ability to explain predictions are also fields of study for machine learning.

Reply on news.ycombinator.com