DEV Community

Cover image for Introduction to Machine Learning
Snehal Adbol
Snehal Adbol

Posted on • Updated on

Introduction to Machine Learning

Introduction to machine learning

Machine Learning has been a buzzword in recent years, owing to the massive quantity of data generated by applications and recent increases in computer power, and the development of better algorithms.

Machine Learning is utilized in various applications, ranging from automating monotonous operations to offering innovative insights; organizations and companies are attempting to profit. You may already be using a gadget that uses it, such as a wearable fitness tracker like Fitbit or an intelligent home assistant like Google Home. However, there are numerous additional examples of ML in action.

What is Machine Learning?

According to Arthur Samuel, machine learning techniques allow computers to learn from data and even improve themselves without being explicitly programmed.

Machine learning (ML) is a method that allows software programs to become more accurate at predicting occurrences without being explicitly programmed. The fundamental concept underlying machine learning is to develop algorithms that can take in input data and use statistical analysis to predict an output while updating results as new data becomes available.

Types of Machine Learning?

Machine learning can be classified into three types of algorithms.
Supervised Learning
Unsupervised Learning
Reinforcement Learning

Overview of Supervised Learning Algorithm

In Supervised learning, an AI system is provided with labeled data, which implies that each data point has been tagged with the correct label.
The aim is to estimate the mapping function so effectively that when you receive new input data (x), you can anticipate the output variables (Y) for that data.
For instance, we have a dataset with pictures of dogs and cats. We display the model labeled photos of dogs and cats while training it, and it learns to classify images into dogs and cats.

Types of Supervised learning

  • Classification: Classification is a strategy for identifying which class the dependent belongs to based on one or more independent variables. Classification is used to anticipate discrete responses.

  • Regression: Regression is the process of determining a model or function for separating data into continuous real values rather than classes or discrete values.

Overview of Unsupervised Learning Algorithm

Unsupervised learning uses machine learning algorithms to evaluate and cluster unlabeled information. These algorithms find hidden patterns or data groupings without the need for human involvement.

Unlike supervised learning, the data is not tagged with the correct label.

For example, Unsupervised learning can help uncover data trends to build more successful cross-selling tactics using prior purchase behavior data. Online sellers utilize this to provide appropriate add-on recommendations to customers throughout the checkout process.

Types of Unsupervised learning

  • Clustering: Clustering is the most significant unsupervised learning issue; like with all other problems of this type, it involves discovering a structure in a set of unlabeled data. 

  • Association: Association rules mining is used to discover new and exciting relationships between items in a collection, a typical pattern in transactional data, or any relational database.

Overview of Reinforcement Learning

Reinforcement Learning is a feedback-based Machine Learning approach in which an agent learns how to behave in a given environment by executing actions and seeing the outcomes of those actions. The agent receives positive feedback, and for each poor action, the agent receives negative feedback or a penalty.
It is a form of dynamic programming that uses a reward and penalty system to train algorithms.

For example, RL in In healthcare is used to propose various treatment choices. While supervised learning models may be used to predict whether or not a person has an illness, RL can predict treatment choices after a person has a disease.

Essentially, by leveraging the incentives received, the agent increases its environment knowledge to choose the following action.

Summary

Machine learning (ML) is a method that allows software programs to become more accurate at predicting occurrences without being explicitly programmed.
What is Machine Learning?
According to Arthur Samuel, machine learning techniques allow computers to learn from data and even improve themselves without being explicitly programmed.

Types of Machine Learning?

  • Supervised learning
  • Unsupervised learning
  • Reinforcement learning

Thanks for reading!

Follow me on github and twitter

Discussion (2)

Collapse
mccurcio profile image
Matt Curcio

Good job!

Collapse
snehal_02 profile image
Snehal Adbol Author

Thank you 😁