Basics of Machine Learning

Arthur Samuel, an expert in the field of Artificial Intelligence and Computer gaming coined the term “Machine Learning” and defined it as “Field of study that gives computers the capability to learn without being explicitly programmed.”

(Arthur Samuel)

Machine learning is a subset of Artificial intelligence. It analyses and interprets patterns and structures in data to enable learning(through training) and then decision making.

Artificial Intelligence: Program with the ability to learn and reason like humans.

Machine Learning: Algorithms with the ability to learn without being explicitly programmed.

Deep Learning: Subset of Machine Learning in which artificial neural network adapt and learn from a vast amount of data.

How does Machine Learning work?

Simply feed the model with an immense amount of data and model will analyze and make a data-driven recommendation.

1. Call the data or Feed the data
2. Write an algorithm to train the data
3. Test the model
4. Find the training and testing accuracy
5. Make predictions

Types of Machine learning:

Machine Learning is of 3 types

Supervised Learning:

In supervised learning human expert acts as a teacher. Human train the computer with the help of training data and the based on that training,the computer or model have to learn and make predictions.

This is task-driven.

The main type of Supervised learning include Regression and classification problems.

Regression,Decession tree,random forest , K-Nearest Neighbour(KNN) and logistic regression are the common algoriths used in Supervised learning.

Unsupervised Learning:

In unsupervised learning computer trained unlabeled data. A human expert does not train the model here, rather the computer teaches human new things after it learns from the pattern of data.

Here we do not have any target to predict. It is used for cluster population or given data in different groups.

This is data-driven.

K-means clustering, Apriori algorithms are the common algorithms used in unsupervised learning.

Reinforcement learning:

This model exposed to an environment where it trains itself continually using train and error.

It learns from its past experience and tries to capture the best possible knowledge to make accurate decisions.

The Reinforcement learning differs from supervised learning in a way that in supervised learning the training data has a correct answer with it so the training of the model is done with the correct answer itself whereas in reinforcement learning there is no answer, so it is bound to learn from its experience.

It can be used in robotics for industrial automation, data processing etc.

Applications of Machine Learning:

1. One of the most common applications of Machine learning is automatic friend tagging suggestion on Facebook or any other social media platform. Face book uses face detection and image recognition to automatically find the face of the person which matches its database.
2. Product recommendations in one of the coolest applications of Machine learning. Google tracks the search history and recommends ads based on search history.
3. Virtual personal assistants like Siri, Alexa, Google Assitance are major applications of machine learning.
4. Companies in the financial sector can identify key insights in financial data as well as prevent any occurrence of financial fraud, with the help of machine learning
5. Based on travel history and pattern of travelling across the various route, Machine learning can help transport companies to predict potential problems that could arise from different routes and accordingly advice their customers to opt for a different route.

and many more

Machine learning is an incredible breakthrough in the field of Artificial intelligence. The applications of Machine Learning is already implemented in various companies across the globe. The machine learning applications are several of many ways which can improve our lives.