Machine learning, a subset of Artificial intelligence (AI), uses computer algorithms to analyze data and make intelligent decisions based on what it’s learned. It can be defined as a method of teaching computers to act upon data without programmed instructions. It is a branch of AI that automatically improves programs using data.
Table of Contents
What is Machine learning?
Machine learning (M.L) is to train computers to learn from past experiences like human beings.
For computers, the word “experience” has another name which is called “Data”.
M.L is the science of getting computers to understand a task without being programmed.
In other words, the big difference between classical algorithms and M.L algorithms lies in the way we define them.
Classical algorithms are given precise and complete guidelines to complete a task.
M.L algorithms are given overall rules that define the model along with data.
This data should contain the missing information necessary for the model to complete the task. So, an M.L algorithm can achieve its task when the model has been updated with respect to the data. We say that we fit the model on the data or that model must be trained on the data.
Explanation
M.L is basically the study of algorithms and statistical models.
It is the training of computer systems to perform a specific task without using explicit instructions, counting on patterns and interference instead.
In other words, Our ability to find out and obtain better tasks through experience is a component of being human. When we are born we know almost nothing and can do almost nothing for ourselves but soon we are learning and becoming more capable every day. Computers can do the same.
M.L brings together statistics and computing to enable computers to find out the way to do a given task without being programmed.
Just as your brain uses experience to enhance a task so can computers. Say you need a computer that can tell the difference between a picture of a dog and a picture of a cat.
You could begin by feeding it images and telling it this one’s a dog and that ones is a cat. A computer programmed to find out the difference between both images will seek statistical patterns within the info which will enable it to acknowledge a cat or dog in the future.
It might figure out on its own that cats have shorter noses and dogs come in a large variety of sizes and then represent that information numerically organizing in space but crucially it’s the computer, not the programmer that identifies those patterns and establishes the algorithm by which future data are going to be sorted.
The more data computer receives the more fine-tunes its algorithm becomes and the more accurate it can be in its predictions.
Machine Learning Examples
Machine learning is already widely applied. It’s the technology behind facial recognition, text to speech recognition, spam filters on your inbox, self-driving cars, medical diagnosis, online shopping or viewing recommendations, stock market analysis, credit card fraud detection and so much more.
At the University of Oxford, researchers are combining statistics and computing to create algorithms that will solve complex problems efficiently, using less computing power. From diagnosis to social media the potential of M.L in the modern world is actually incredible.
Facebook uses M.L to develop users’ data and feedback to individualize their feeds. If you like a post, the algorithm learns from this and starts to show you similar content. This is a continuous process and so the material indicated in your newsfeed evolves with your preferences making your experience more enjoyable. Apple can identify your friend’s face in the photo you just took. Amazon echo understands you and can answer your questions. Netflix recommends videos that match your profile. M.L has become a substantial part of our daily lives and it’s not going anywhere soon.
How Does Machine Learning Work?
Machine learning can be illustrated with a simple example, let’s say we want to predict the price of a house based on the size of the house, the size of its garden, and the number of rooms It has.
We could try to build a classical algorithm that answers this problem. This algorithm would have to take the three house features and return the predicted price based on an explicit rule. In this example, the exact house pricing formula has to be known and coded explicitly but in practice, this formula is often not known.
On the other hand, we can build an M.L algorithm first, such algorithms would define a model that can be an incomplete formula created from our limited knowledge, then the model would be adjusted by training and giving housing prices examples. In doing so we combine a model with some data.
In general, M.L is incredibly useful for difficult tasks, when we have incomplete information or information that’s too complex to be coded by hand. In such cases, we can give the available information to our model and let this to learn the missing information that it needs by itself.
The algorithm uses statistical techniques to extract the missing knowledge directly from the data. The two main categories of M.L techniques are
- Supervised learning
- Unsupervised learning
Supervised Machine Learning
In Supervised learning, we want to get a model to predict the label of the data based on their features. In order to learn the mapping between features and labels, the model has to be fitted on given examples of features with their related labels. We say that the model is trained on the labeled data set. Predicted labels can be numbers or categories, for example, we could be building a model that predicts the price of a house implying we would want to predict a label that’s a number. In this case, we would talk about the regression model.
Unsupervised Machine Learning
In Unsupervised learning, we want to define a model that reveals structures in some data that are described only by their features but with no labels. for example, unsupervised learning algorithms can help answer questions like are their groups among my data or is there any way to simplify the description of my data.
The model can look for different kinds of underlying structures in the data. If it tries to find groups among the data, we would talk about the clustering model. an example of a clusterin model, would be a model that segments customers of a company based on their profiles. Otherwise, if we have a model that transforms data and represents them with a smaller number of features we would talk about the dimension reduction model. An example of this would be a model that summarizes the multiple technical characteristics of some cars into a few main indicators.
Summary
Machine learning has two major categories, supervised learning and unsupervised learning.
In supervised learning, models associate a label with each data point described by its features whereas unsupervised learning models find structures among all the data points.
In a sense, supervised learning is similar to learning the names of fruits from a picture book. You associate the characteristics of the fruit, the features, and the names written on the page “the label”. Classical examples of supervised learning algorithms are linear regression, logistic regression, support vector machines, neural networks, and so on.
More Interesting Links
What Is Google Jamboard
3D Printing| Additive Manufacturing
What Is A Search Engine?
What is Cloud computing?
Please send any feedback to [email protected]
- BCl3 Lewis Structure in four simple steps - November 1, 2023
- PH3 Lewis Structure in four simple steps - October 8, 2023
- PF3 Lewis structure in four simple steps - September 24, 2023
What is Artificial Intelligence? - What's Insight
Saturday 28th of November 2020
[…] at analyzing vast amounts of data to learn to complete a particular task, a technique called machine learning. But AI’s not good at transferring what it has learned from one type of task to another; […]
Sara
Tuesday 24th of November 2020
What are job opportunities for data scientist?