Exponential Functions Since the Independent variable occurs in the Exponent...
There are two types of Machine learning, they are, Supervised Machine learning and Unsupervised Machine learning.
Supervised Machine learning: Here the designer observes and directs the execution of a task, project or activity. The best example here would be, you working under a project manager.
You are assigned a set of tasks and you are expected to follow instructions, you have no right to put in, either your creativity or your common senses into action. In other words, you are to do what you are told to do.
Just that in Machine learning, we would be supervising a Machine learning Model. How do we do that? We load the model with knowledge so that the model is trained to predict future instances.
So how do we teach the model. We teach the model by what we call as training data, we explicitly tell the machine the data that is input and the expected output for the data.
It is imperative to understand that the above illustration is merely the most basic one. Depending on the Domain that we are dealing with, the requirements and the demands may vary. Thus, to handle the demands of the Domain, we have different Algorithm models available to handle the challenges.
Types of Supervised learning Algorithm
It is important to note here that the ones specified above are not the complete inclusive list. Given the flexibility of Algorithms, there are many, in fact, you can come up with an Efficient working Algorithm, tomorrow, to replace an existing one.
In unsupervised learning, the data is not labeled, yet still, we input this data into the Machine learning Algorithm, get it Processed and obtain the Trained Model.
The Trained Model will predict the pattern. The best feature about unsupervised learning is that the machine functions independently. Though there are some advantages in this model, yet still, this model cannot be the go to model for all most requirements.
As with the Supervised learning, here too we have a list of Algorithms that are popularly applied depending on the domain requirements.