Machine Learning From Scratch for Beginners
We all know how AI & Machine learning is evolving day by day. ML will of course be the most transformative technology of the next decades. The Machine Learning Engineer career path is the most desiring and promising one in the field of Data Science as well. Machine Learning will influence every field like the way we communicate, traveling, shopping, routine tasks, business sectors, etc., According to Indeed, Machine learning Engineer is the best job with growth at its peaks and an average salary of $146,085 per annum.
Let us know the actual definition of Machine Learning.
According to Arthur Samuel in 1959,
ML is defined as a field of study that gives computers the ability to learn without being explicitly programmed.
According to Tom Mitchell in 1998, Machine learning is defined as
A computer program is said to learn from experience E with respect to some task T and some performance measure P, if its performance on T, as measured by P, improves with experience E.
In simple words, If we fetch input and output data to the machine learning model, it gives us the result as rules to be performed or followed.
Example:
Suppose we have a problem about whether the payment is done or not for the available bills. Here the input is available bills and the output is payment is done or not. So let the machine learning use this data to create the model.
As we can see in the above image where rules are generated in the ML model. This can be used to predict business outcomes in any situation where you have input and past output data.
Types of Machine Learning:
Supervised Learning:
In Supervised learning, we will be having an Input dataset and already know what our correct output should look like, having the idea of a relationship between the input and the output.
An example is given below:
By seeing the above image, we can clearly understand supervised learning.
Supervised learning problems are classified into regression and classification as shown below:
In regression, we are trying to predict results in the continuous output whereas, in classification, we are trying to predict results in the discrete output.
Example of Regression:
You had given an image of a person and we had to predict the age of a person on the basis of a given picture.
Example of Classification:
Given a patient with a tumor, we have to predict whether the tumor is a malignant or benign tumor.
Unsupervised Learning:
Unsupervised learning allows us to approach problems with slight or no idea about how our results look like.
We can derive this structure by clustering the data based on relationships among the variables in the data.
Unsupervised Learning classified into Clustering and Non-Clustering.
Clustering Example: Take a collection of 2,00,000 different species and find out a way to automatically group these species into groups that are somehow similar or related by different variables such as life, span, location, and so on.
Non-Clustering Example: The “Cocktail party Algorithm” allows you to find structure in a chaotic environment i.e., identifying individual voices and music from a mesh of sounds at a cocktail party.
Reinforcement Learning:
Reinforcement Learning is a feedback-based technique where an agent learns to behave in an environment by performing the actions and seeing the results of actions. For every good action, the agent gets positive feedback, and for each bad action, the agent gets negative feedback or penalty.
Reinforcement Learning is a core part of Artificial Intelligence and agents work on the concept of reinforcement learning. We don't need to pre-program the agent, as it learns from its own experience without any human intervention.
Follow this page for related blogs:
