Machine Learning Is Fun!!!

We know humans learn from past experiences and machines follow instructions given by humans, but what if humans can train the machines to learn from the past data and do what humans can do act much faster, that’s called Machine Learning.

For example, 1 method is the classification method. It can put data into various groups. The same classification method used to concede handwritten numbers and also be used to classify emails into spam and not-spam. It is the same method but it’s fed different training data and hence it comes up with different classification logic.

There are three types of Machine Learning Algorithms:

• Supervised Learning

• Unsupervised Learning

• Reinforcement Learning

Supervised Learning:

Here we have a teacher who gives us instructions i.e training data, which means here in supervised learning we have inputs also and outputs also and through that given data also known as labeled data we prepare a model and there we put our new I puts and check whether we are getting desired output or no and if we get the same output as per training data, the data given was very accurate and refined and the algorithm is properly learned and classified, and the algorithm used here is Naive Bayes Algorithm.

Unsupervised Learning:

Unsupervised learning is something where we only have some inputs, and from the available and known inputs, we make clusters or groups according to

similar inputs. Here we do not have outputs, so we have to generate it by using K-Mean Algorithm. Maximum learning is done through unsupervised learning.

Reinforcement Learning:

Now here, this learning is based on reward and policy. For eg. We have an agent who performs some action in the environment and in return, the agent gets some reward/penalty based on the action performed may be positive or negative. So according to the change in environment, the agent makes the policy, and based on the policy he performs his actions in a different manner. So here from the rewards and penalties, learning is done.

Some of the exciting examples of Machine Learning are:

1. Virtual Personal Assistants

Siri, Alexa, Google Now are some of the well-known examples of virtual personal assistants. As the name suggests, they assist in finding specific information, when asked over voice. All you need to do is activate them and ask “What is my schedule” or maybe “Read the messages” or maybe set any alarm and accordingly u get answered.

Virtual Assistants are integrated into a variety of platforms. For example:

• Smart Speakers: Amazon Echo and Google Home

• Smartphones: Samsung Bixby on Samsung S8

• Mobile Apps: Google Allo

2. Predictions while Commuting

Traffic Predictions: We use our GPS locations randomly while traveling, so that detects our current location as well as the location where we want to reach and guide us accordingly. Also, we are guided by the traffic ahead and various routes we can go through.

Online Transportation Networks: While we book an ola or cab, the price is estimated automatically. In this entire cycle, Machine Learning plays a very important role.

Read Full Article here: Machine Learning

For more Articles visit here: Articles