Introduction to Machine Learning: Supervised and Unsupervised Learning

  • Tanesh Balodi
  • Sep 06, 2019
  • Machine Learning
Introduction to Machine Learning: Supervised and Unsupervised Learning title banner

We are living in a world of Humans and Machines. Humans have been learning and evolving from the past experience for billions of years, on the other hand, the era of machines and robots has just begun.

 

In today’s world, these machines or robots need to be instructed to perform, but what if machines started to learn from their own and this is where machine learning comes into the picture.

 

Topics Covered

 

  1. What is Machine Learning?

  2. How does Machine Learning work?

  3. Different type of Machine Learning

 

What is Machine Learning?

 

Machine learning is the core of much futuristic technological advancement in our world, today you can see various examples or implementation of machine learning around us such as Apple series, Tesla’s self-driving car, Sophia AI robot and many more are there. So what exactly is Machine Learning? “Machine Learning is a subset of artificial intelligence. It focuses mainly on the designing of systems, thereby allowing them to learn and make predictions based on some set of matrices in machines”.

 

Do you know why is Machine Learning important, how does it work, what are the different types of Machine Learning or where is it headed? – So, let’s dive into the answer to these questions one after another. The value of Machine learning has just begun to show itself, there’s a lot of data in the world today generated not only by people but also by computers, mobile phones, and other devices. This data is in continuation to increase as a number of user increases.

 

Traditionally, humans have analyzed data and adapted their culture from their past data. However, as the volume of data exceeds the ability for the human approach, it becomes possible to quickly and automatically produce models that can analyze bigger, more complex data and deliver faster, more accurate results – even on a very large scale.

 

 

How does Machine Learning work?

 

One of the approaches is where the machine learning( ML) algorithm is trained using a labelled or unlabelled training data set to produce a model. New input data is introduced to the ML algorithm and make a prediction based on the model, the prediction is then evaluated for accuracy and if the accuracy is acceptable the machine learning algorithm is deployed.

 

But, what if the accuracy is not acceptable, the ML algorithm is trained again and again within an augmented training data set, this was just a high-level example as there are other steps involved in it. Let’s move on and quickly parse through Machine learning into different types, see how each of them are, how they worked and how each of them is used in various fields.

 

 

Types of Machine Learning

 

  1. Supervised Learning

  2. Unsupervised Learning

  3. Reinforcement Learning


Machine learning algorithms divided into three main categories, supervised, unsupervised and reinforcement learning. Analytics Steps

Types of Machine Learning


 

Supervised Machine Learning

 

In supervised learning, you train your model on a labelled dataset that means we have both raw input data as well as its results. We split our data into a training dataset and test dataset where the training dataset is used to train our network whereas the test dataset acts as new data for predicting results or to see the accuracy of our model.

 

Hence, in supervised learning, our model learns from seen results the same as a teacher teaches his students because the teacher already knows the results. Accuracy is what we achieve in supervised learning as model perfection is usually high.

 

The model performs fast because the training time taken is less as we already have desired results in our dataset. This model predicts accurate results on unseen data or new data without even knowing a prior target. In some of the supervised learning models, we revert back the output result to learn more in order to achieve the highest possible accuracy.

 

For each input instance an expected value associates, the value can be discreetly presenting a category or it can be real or continuous value. The algorithm learns the input patterns that generate the expected output and now once the algorithm is trained it can be used to predict the correct output of a never seen input.


Supervised learning in machine learning example

Supervised Machine Learning


In this image above you can see that we are feeding raw inputs as an image of apple to the algorithm as a part of the algorithm we have a supervisor who keeps on correcting the machine or who keeps on training the machines or keeps on telling him that yes it is an apple or no it is not an apple, things like that.

 

So this process keeps on repeating until we get a final trained model, once the model is ready it can easily predict the correct output of a never seen input.

 

Some algorithms for supervised learning

 

  1. Linear Regression

  2. Random Forest

  3. Support Vector Machines (SVM)

 

 

Applications of Supervised Learning

 

  • Sentiment Analysis: It is a natural language processing technique in which we analyze and categorize some meaning out of the given text data. For example, if we are analyzing tweets of people and want to predict whether a tweet is a query, complaint, suggestion, opinion or news, we will simply use sentiment analysis.

 

  • Recommendations: Every e-Commerce site or media, all of them use the recommendation system to recommend their products and new releases to their customers or users on the basis of their activities. Netflix, Amazon, Youtube, Flipkart are earning huge profits with the help of their recommendation system.

 

  • Spam Filtration: Detecting spam emails is indeed a very helpful tool, this filtration techniques can easily detect any sort of virus, malware or even harmful URLs. In recent studies, it was found that about 56.87 per cent of all emails revolving around the internet were spam in March 2017 which was a major drop from April 2014's 71.1 per cent spam share.

 

 

Unsupervised Learning

 

In unsupervised learning, the information used to train is neither classified nor labelled in the dataset. Unsupervised learning studies on how systems can infer a function to describe a hidden structure from unlabelled data. The main task of unsupervised learning is to find patterns in the data.

 

Once a model learns to develop patterns, it can easily predict patterns for any new dataset in the form of clusters. The system doesn’t figure out the right output, but it explores the data and can draw inferences from datasets to describe hidden structures from unlabeled data.


Unsupervised Learning in Machine Learning example. Analytics Steps

Unsupervised Learning 


As we have already discussed that in unsupervised learning our dataset is not labelled, So if we are feeding apple, carrot, and cheese as raw input data then our model will distinguish all three but it cannot tell whether a given cluster is of apple or not as it is unlabelled but any new data will automatically fit into the clusters that are formed.

 

Some algorithms available for unsupervised learning are

 

  1. Principal Component Analysis Algorithm

  2. K-means Algorithm

  3. Singular Value Decomposition Algorithm

 

Applications of Unsupervised Learning

 

  • Document Clustering: In order to retrieve some information out of a text document we use techniques like K-means, it is also used to organize the document, topic extraction as well as filtering.

 

  • Data Reduction: visualizing and analyzing data with thousands of dimensions is a hectic task for machine learning models as they break down sometimes after a while, and after that data does not correlate with each other. In order dimensions to prevent dimension related problem, we use unsupervised algorithms such as singular value decomposition or principal component analysis.

 

  • Unsupervised learning is used for Anomaly Detection where it can help in the detection of any sort of fraud by observing unusual data points in the dataset. It is also used for outliers detection in which we differentiate all the outliers in the available dataset.

 

 

Reinforcement Learning

 

It is a Machine Learning algorithm that allows software agents and machines to automatically determine the ideal behaviour within a specific context to maximize its performance. It does not have labelled dataset or results associated with data so the only way to perform a given task is to learn from experience.

 

For every correct action or decision of algorithm, it is rewarded with positive reinforcement whereas, for every incorrect action, it is rewarded with negative reinforcement. In this way, it learns which actions are needed to perform and which are not. Reinforcement learning can, therefore, help in industrial automation as well as the gaming sector primarily.


Reinforcement Learning in Machine Learning Example

Reinforcement Machine Learning


Let's understand reinforcement learning by this example in this agent gives itself a reward with correct actions or predictions to improve its environment. So basically, this agent is supposed to get more and more rewards to get better results or achieve goals. Lastly, whichever environment of agents creates better result it will be our best possible model.

 

Applications of Reinforcement Learning

 

  • Robotics: Reinforcement learning is used in the advancement of robotics. These models are used to train robots so that they can learn from their experience which is a belief of reinforcement learning.

 

  • Traffic Light Management System: Reinforcement Learning model that was applied to the traffic management system provided better results in comparison to the traditional method for the congestion problem.

 

  • Personalized Recommendation: Deep Reinforcement learning can perform better results in personalized recommendation than other ML models, it performed greatly on news recommendation which consisted of the challenges like dynamic news, click-through rate and more.

 

 

Conclusion

 

Machine learning uses algorithms to parse data, learn from that data, and make informative decisions based on what it has learned. The above information has certainly helped you in deciding if you will use supervised, unsupervised or reinforcement learning. For more blogs in Analytics and new technologies do read Analytics Steps.

0%

Tanesh Balodi

A splendid and inventive Machine Learning Intern in Analytics Steps. He loves deploying data in ML and finds out different insights to play with industry trends.

Trending blogs

  • What is the OpenAI GPT-3?

    READ MORE
  • Introduction to Time Series Analysis: Time-Series Forecasting Machine learning Methods & Models

    READ MORE
  • How is Artificial Intelligence (AI) Making TikTok Tick?

    READ MORE
  • 6 Major Branches of Artificial Intelligence (AI)

    READ MORE
  • 7 Types of Activation Functions in Neural Network

    READ MORE
  • 7 types of regression techniques you should know in Machine Learning

    READ MORE
  • Top 10 Big Data Technologies in 2020

    READ MORE
  • Reliance Jio and JioMart: Marketing Strategy, SWOT Analysis, and Working Ecosystem

    READ MORE
  • Introduction to Logistic Regression - Sigmoid Function, Code Explanation

    READ MORE
  • What is K-means Clustering in Machine Learning?

    READ MORE
  • 360digitmgsd

    Jun 15, 2020

    You explained the unsupervised in an interesting which people can understand easily. <a href="https://360digitmg.com/india/data-science-using-python-and-r-programming-aurangabad">data science training in aurangabad</a>

  • 360digitmgsd

    Jun 15, 2020

    You explained the unsupervised in an interesting which people can understand easily.

  • 360digitmgbs

    Jun 18, 2020

    I finally found great post here.I will get back here. I just added your blog to my bookmark sites. thanks.Quality posts is the crucial to invite the visitors to visit the web page, that's what this web page is providing. <a href="https://360digitmg.com/india/data-science-using-python-and-r-programming-vijayawada">data science training in vijayawada</a>

  • Write a BLOG