10 Basic Machine Learning Interview Questions

Machine learning interview questions are one of the most important part in data science interview.There are some answers to go along with them so you don’t get stumped. You’ll be able to tackle basic questions on machine learning in any job interview after reading through this piece.


What is Machine Learning?

Machine learning is a field of study that gives computers ability to learn without being explicitly programmed. 
                                            or
A computer is said to learn from experience E with respect to some task T and some performance measure P, if it's performance on T as measured by P increases with E.

 What are the types of Machine Learning? 

-Supervised learning
-Unsupervised learning
-Reinforcement learning
-Recommendation system



 What do you mean by training sample?

     A training sample is a data point x in an available training set that we use for tackling a predictive modeling task. For example, if we are interested in classifying emails, one email in our data set would be one training sample. Sometimes, people also use the synonymous terms training instance or training example.
     

     What do you understand by the term Regression?

 A technique for determining the statistical relationship between two or more variables where a change in a dependent variable is associated with, and depends on, a change in one or more independent variables.
     

     What is Target Function?


In predictive modeling, we are typically interested in modeling a particular process; we want to learn or approximate a particular function that, for example, let's us distinguish spam from non-spam email. The target function f(x) = y is the true function f that we want to model.




What is Hypothesis?

A hypothesis is a certain function that we believe (or hope) is similar to the true function, the target function that we want to model. In context of email spam classification, it would be the rule we came up with that allows us to separate spam from non-spam emails.
                                         OR
       A hypothesis is an assumption about a particular situation of the world that is testable.
      

     What do you mean by NULL hypothesis?

An example. I am accused of murder. The null hypothesis is that I am not guilty, because the legal principle is that I am innocent until I am proven guilty. Since the null hypothesis must be constructed before you examine the evidence it must be that I am not guilty. The alternative hypothesis is that I am guilty. If the evidence is sufficiently persuasive, you will shift your belief from the null hypothesis to the alternative hypothesis.


What is a Machine Learning Model?


 In machine learning field, the terms hypothesis and model are often used interchangeably. In other sciences, they can have different meanings, i.e., the hypothesis would be the "educated guess" by the scientist, and the model would be the manifestation of this guess that can be used to test the hypothesis.


What do you mean by Learning Algorithm?

Again, our goal is to find or approximate the target function, and the learning algorithm is a set of instructions that tries to model the target function using our training data-set. A learning algorithm comes with a hypothesis space, the set of possible hypotheses it can come up with in order to model the unknown target function by formulating the final hypothesis



How will you define term Classifier?

  A classifier is a special case of a hypothesis (nowadays, often learned by a machine learning algorithm). A classifier is a hypothesis or discrete-valued function that is used to assign (categorical) class labels to particular data points. In the email classification example, this classifier could be a hypothesis for labeling emails as spam or non-spam. However, a hypothesis must not necessarily be synonymous to a classifier. In a different application, our hypothesis could be a function for mapping study time and educational backgrounds of students to their future SAT scores.




Comments