whats the difference between machine learning and statistics?_问答_开发者

in the Turing lecture 2010 Christopher Bishop talks about machine learning undergoing a revolution because statistics is being applied to machine learning algorithms...

but then its like all machine learning algorithms are all statistical algorithms.. whats the real diff开发者_StackOverflowerence between the two? why are they separate courses in most universities?

Statistics bases everything on probability models. A typical analysis starts by assuming your data are samples from a random variable with some distribution, then making inferences about the parameters of the distribution.

Machine learning may use probability models, and when it does, it overlaps with statistics. But machine learning isn't so committed to probability. It is willing to also use other approaches to problem solving that are not based on probability.

There isn't a great deal of difference between the two, and what there is is mostly cultural. Machine Learning came from Computer Science roots whereas Statistics is more mathematical. There's a nice blog post called "Statistics vs. Machine Learning, fight!" by Brendan O'Connor that talks about this.

As for non-statistical approaches to machine learning, well there are several rule-based approaches (decision trees, rule induction, ILP) and there are also approaches like reinforcement learning for control problems. Those don't feel very statistical to me, but you could claim that they are... you could probably claim all of life falls under statistical decision theory if you wanted to (in fact, Marcus Hutter does).

I can see some important differences:

#Scope: Machine learning uses statistical models, but it also uses other models such as dynamic programming, reinforcement learning, techniques that came from Artificial Intelligence or optimization.

#Point of View: Statistics is usually concerned with the properties of the estimators (unbiasedness, assymptotic behavior) and machine learning is mainly concerned with the solution of real world problems.

#Reasearch field: While Statistics can be seen as a subfield of Applied Mathematics, Machine Learning can be seen as a subfield of computer science.

#Code development and application: While people who work with statistics usually has a prefference for R (or SAS, STATA, EVIEWS), people who work with machine learning usually chooses Python (or another structured programming language)

Maybe it's worth to point out that similar question is being addressed and discussed at CrossValidated

Statistics focuses on all aspect of data-analysis such as descriptive, exploratory, inferential, predictive and causal. But, machine learning only focus on predictive modeling.

Machine Learning is

An algorithm that can learn from data without relying on rules-based programming.
A subfield of computer science and artificial intelligence which deals with building systems that can learn from data, instead of explicitly programmed instructions.

Statistical Modelling is

Formalization of relationships between variables in the form of mathematical equations.
Subfield of mathematics which deals with finding relationship between variables to predict an outcome

A machine learning system is truly a learning system if it is not programmed to perform a task, but is programmed to learn to perform the task. It is a data-driven exercise. Modern machine learning does not rely on a rich set of algorithmic techniques. Almost all applications of this form of machine learning are based on deep neural networks. This is the area we now tend to call Deep Learning, a specialization of Machine Learning, and frequently applied in weak Artificial Intelligence applications, where machines perform a human task.

In ML, the idea is that you build a separate model for the situation, where you have the data versus you don't have the data.

Statistics, on the other hand, is about keeping the data that you have and getting the best result of the data.

The difference is philosophy affects how you treat outliers. In ML, you go out and find enough outliers that become something that you can actually train with.

With Statistics you say, "I've got all the data I'll ever be able to collect." So, you throw out outliers. It's a Philosophical difference because of the scenarios where ML and statistic are used.

Statistics is often used in a limited data regime or ML operates with lots of data.

Machine learning :

Machine learning is the science of making computers learn and act like humans by feeding data and information without being explicitly programmed.

Example: When we coming to the computer, Writing a peace of code or program and telling the computer step by step to do. But ML we don't do that, the system learns on its own. We just provide the past data(called labelled data) and the system learns during the process what is known as training process, we tell the system the system the outcome are right or wrong, that feedback is taken by system and it corrects itself and that's who its learns, it gives the correct output of the most of the cases. Obviously it is not 100% correct but aim is to get as accurate as possible.

Statistics:

It is a field of mathematics which is used to find the relationship between different variables.

Main difference:

Statistics: Focus on formalisation of relationship between variables in the form of mathematical equations.

Machine learning: Comprises of algorithms that can learn from data without relying on rules based programming.

Machine learning is developed by computer scientists while Statistics is developed by mathematicians. Machine learning is built upon statistical frameworks. Statistics was developed in the 17th century, MAchine learning was developed in 1959. Machine learning is a subfield of Artificial Intelligence. Statistics is a subfield of Mathematics. Machine learning finds the generalizable predictive patterns while statistics draw population inference from a sample. Machine learning is a BlackBox approach. Statistics opens the BlackBox. Machine learning needs a very large amount of data and attributes while Statistics need less. Statistics require mathematical knowledge. Machine learning requires both mathematical and algorithms knowledge. Statistics use the correlation between the data points while machine learning is used for making a hypothesis. ML makes fewer assumptions than statistics. Machine learning has more predictive power. Machine learning requires less human effort than statistics. Machine learning uses algorithms. Statistics uses equations. They use different tools

YOu can find more in this article I found: https://www.thejay.tech/2020/01/the-actual-difference-between.html