What is Machine Learning ?

Machine Learning ” when this two words comes to our mind it can mean several things like machines can automatically learn,system which learn by itself given some information etc all this definition are correct ,the more accurate definition i.e given by Tom Mitchell ” A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T, as measured by P, improves with experience E “. Let me make it simple normally Machine Learning is an application of Artificial Intelligence, that provides the system the ability to learn automatically and improve from experience without being explicitly programmed.

One might ask “Why should machines have to learn? Why not design machines to perform as desired in the first place ?” There are several reasons why machine learning is important .Of course , the achievement of learning in machine might help us understand how animals and human learn.But there are important engineering reasons as well.Some of these are:

  • Some task cannot be defined well except by example; that is ,we might be able to specify input/output pairs but not a concise relationship between inputs and desired outputs.We would like machine to able to adjust their internal structure to produce correct outputs for large number of sample inputs an thus suitably constrain their input/output function to approximate the relationship implicit in the example
  • It is possible that hidden among large piles of data are important relationships and correlations.Machine Learning methods can often be used to extract these relationships this is also called data mining.
  • Environments change over time.Machines that can adapt to a changing environment would reduce the need of constant design.
  • The amount of knowledge available about certain task might be too large for explicit encoding by humans.Machines that learn this knowledge gradually might be able to capture more of it that humans would want to write down.

A real life Example of Machine Learning

Product Recommendation

You all are frequently or regularly using the ecommerce sites like Flipkart ,Snapdeal, Amazon and many others , then you might have noticed that the shopping website or the app recommends you some items that somehow matches with your taste. So what this websites are doing they are running a machine learning algorithm on their backend which is monitoring your previous purchases , and also your behaviour (like which product you mostly searched ,or mostly viewed etc) , after collecting all this data they use a ML algorithm that can recommend a product which you will most likely to buy in the near future.

Varieties Of Machine Learning

In any learning technique it is more important question of what is to be learned we take it that the thing to be learned is the computational structures of some sort.Here we are considering a variety of different computational structures:

  • Functions
  • Logic programs and rule sets
  • Grammars
  • Problem solving systems

The change of the existing structure might be simply to make it more computationally efficient rather than to increase the converge of the situations it can handle.

Different Types of Learning

Supervised Learning

It is a type of algorithm in which we have or we know the target/output variable/or the variable which our model will predict,In more simple terms we are given a data that have a set of independent variable X={x1,x2,x3…….., xn} (n number of features) and also a set of dependent variable Y={y1,y2,y3………,yn}(Target) (Y is dependent on X) so with the help of the features/independent variable and the dependent variable whatever you call it our model will learn some patterns or correlation between the features and our target variable so latter when we give our model some random features as input it will be able to predict the dependent variable or the target variable.

Example-If we want to predict the price of a house depending on certain features like area per square feet, location, size etc and our target variable is price here, because we want our model to predict the price of house .So imagine if we have a large data set containing 10000 data of price of house and its features.So we can train our model with the help of this data so latter when we give some random features like area , location,and size our model can predict the price of the house so this is an example of supervised learning as we train our model with the help of both dependent variable(features) and independent variable(target).

Types of Supervised Learning :

Regression- A regression problem is when the output variable is a real or continuous value, such as “salary” or “weight” , “price” example is same as mentioned above. 

Types of Regression models :

  • Linear Regression
  • Lasso Regression
  • Ridge Regression
  • Polynomial Regression
  • Support Vector Machine
  • Decision Tree
  • Naive Bayes(not much recommended for regression problems)
  • Neural Network
  • Random Forest

Classification- A classification problem is when the output variable is a category, such as “red” or “blue” or “disease” and “no disease”. A classification model attempts to draw some conclusion from observed values. Given one or more inputs a classification model will try to predict the value of one or more outcomes.
For example, when filtering emails “spam” or “not spam”, when looking at transaction data, “fraudulent”, or “authorized”. In short Classification either predicts categorical class labels or classifies data (construct a model) based on the training set and the values (class labels) in classifying attributes and uses it in classifying new data.

Types of Classification models :

  • Logistic Regression
  • Decision Tree
  • Random Forest
  • Naive Bayes
  • Support Vector Machine
  • KNN( K -Nearest Neighbor)
  • Neural Network

Unsupervised Learning

Clustering in this algorithm we don’t have any dependent variable or target variable to predict.It is used for clustering or grouping population(unlabeled data set) in different groups , each group contains the data which have similar tastes.It is widely used for segmenting customers in different groups for specific intervention.

Types of Clustering Algorithm :

  • K- Means Clustering
  • Hierarchical clustering
  • Gaussian Mixture Model

Association:  An association rule learning problem is where you want to discover rules that describe large portions of your data, such as people that buy X also tend to buy Y.

Semi Supervised Learning

Problems where you have a large amount of input data (X) and only some of the data is labeled (Y) are called semi-supervised learning problems.

These problems sit in between both supervised and unsupervised learning.

A good example is a photo archive where only some of the images are labeled, (e.g. dog, cat, person) and the majority are unlabeled.

Many real world machine learning problems fall into this area. This is because it can be expensive or time-consuming to label data as it may require access to domain experts. Whereas unlabeled data is cheap and easy to collect and store.

You can use unsupervised learning techniques to discover and learn the structure in the input variables.

You can also use supervised learning techniques to make best guess predictions for the unlabeled data, feed that data back into the supervised learning algorithm as training data and use the model to make predictions on new unseen data.


One thought on “What is Machine Learning ?

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s