Blog

Introduction to Machine Learning

What is Machine Learning?

“Machine learning is the science of getting computers to learn and act like humans do and automatically improve their learning over time, by feeding data and information in the form of observations and real-world interactions.”

Different types of learning in Machine Learning

There are 3 types of major machine learning algorithms:

  • Supervised Learning
  • Unsupervised Learning
  • Reinforcement Learning
1. Supervised Learning

A supervised learning algorithm has the ability to learn from labeled training data and once the input data goes through the machine learning algorithm, the trained models are capable of predicting the outcomes for unforeseen data.

Types of Supervised machine learning algorithms:

  • Classification
  • Regression
Classification

Classification algorithms are used when the response variable is in a categorical form. The following are the algorithms used in classification algorithms:

  • Random Forest
  • Support Vector Machine
  • Logistic Regression
  • Decision trees
Regression

Regression algorithms are used when there is a relationship between the input data and the response variable. This algorithm is used in predicting continuous variables such as market price, weather forecasting etc. The following are the algorithms used in regression algorithms:

  • Linear Regression
  • Regression Trees
  • Non-Linear Regression
  • Bayesian Linear Regression
  • Polynomial Regression
2. Unsupervised Learning

Unlike in supervised learning, this technique uses unlabeled training data set. Instead of providing the labeled data, this kind of model itself identifies the hidden patterns and insights from the training data set.

Once the unlabeled input data is fed to the machine learning model, it is capable of interpreting the raw data to find the hidden patterns and the algorithm divides the similar data objects into the same group.

Clustering is the most common unsupervised learning technique. It is a method of grouping objects into clusters such that the similar objects fall into one group. The following are the algorithms used in Clustering algorithms:

  • K-means clustering
  • K- Medoids clustering
  • Hierarchical clustering
  • Neural Networks
3. Reinforcement Learning

Reinforcement learning differs from supervised learning in a way that in supervised learning, the training data has the output with it, so the model is trained with the correct answer itself. In reinforcement learning, it has no output, but the agent decides what to do to perform the given task and it is bound to learn from its experience.

When a reinforcement learning solution performs a task correctly, it receives positive feedback which strengthen the model in connecting target inputs and output. Also, it can receive negative feedback for incorrect solutions.

Real-World Applications of Machine Learning
  • Image Recognition
  • Speech Recognition
  • Product Recommendations
  • Self-Driving cars
  • Medical Diagnosis
  • Fraud Detection
  • Text Analysis