What is Machine Learning?

Machine learning is an application of artificial intelligence (AI) that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. A machine learning algorithm is the “learning” model which allows the algorithm to learn from the data and make its own decisions. This allows machines to perform tasks which are otherwise are impossible for it to perform. Such tasks can be as simple as recognizing human handwriting or as complex as self-driving cars!

Machine learning algorithms are often categorized as supervised or unsupervised learning

1. Supervised Learning:

In Supervised learning, we have prior knowledge of what the output values for our samples input should be. Therefore, the goal of supervised learning is to learn a function that, given a sample of data and desired outputs, best approximates the relationship between input and output observable in the data.

Supervised learning is done in the context of classification when we want to map input to output labels, or regression when we want to map input to a continuous output. Common algorithms in supervised learning include logistic regression, naive Bayes, support vector machines, artificial neural networks, and random forests.

2. Unsupervised Learning:

Unsupervised learning does not have labeled outputs, so its goal is to infer the natural structure present within a set of data points. The most common tasks within unsupervised learning are clustering, representation learning, and density estimation. In all of these cases, we wish to learn the inherent structure of our data without using explicitly-provided labels. Some common algorithms include k-means clustering, principal component analysis, and autoencoders. Since no labels are provided, there is no specific way to compare model performance in most unsupervised learning methods. For example: if we want to categorize the similar type of customers based on their purchasing behavior then we can use clustering. clustering basically group/cluster the similar data points

3. Reinforcement Learning

Reinforcement machine learning algorithms is a learning method that interacts with its environment by producing actions and discovers errors or rewards. Trial and error search and delayed reward are the most relevant characteristics of reinforcement learning. This method allows machines and software agents to automatically determine the ideal behavior within a specific context in order to maximize its performance.

How does Machine Learning work?

Let us see step by step process how we train our Machine Learning Models

• In the first step, we just collect the raw data, and we apply it as input data.
• Then in the second we do some preprocessing of the data like handling NULL values, standardization, handling categorical values and then visualizing the data, extracting useful information and removing the outliers to make the data in the useful formate and most important feature selection/ feature extraction.
• After doing all this then we decide what type of Machine algorithm we should apply whether we should apply classification, regression or clustering it totally based on our problem statement what we going to solve. Example: suppose if we want to correctly distinguish between a male and a female face from ID-card photos what we will use classification and suppose if we want to predict the home price based on given features we will use regression.
• Now our next step after choosing the machine learning algorithm and then apply it on our data set so that model will able to learn from the given dataset and then and based on training it will able to take the decision based on its learning. During this, there are lots of hyperparameter tuning that is to be done so that to increase the performance of the Machine learning model, so that it can predict or take decision better.

let me explain you with an example so that you can understand better

For example, say an algorithm is supposed to correctly distinguish between a male and a female face from ID-card photos.

Input

So as an input we provide the user data and machine learning (ML) algorithm would be trained on a training data to ‘learn’ using data and to recognize the user where the user is male or female. or given a user image as data, machine learning (ML) algorithm would be trained on training data to ‘learn’ to recognize any face. Where a simple algorithm would not be capable of performing this task, an ML algo would not only be able to categorize the photos as training, it would continuously learn from testing data and add to its “learning” to become more accurate in its predictions! Recall how often Facebook prompts you to tag right the person in the picture! Among billions of users, Facebook ML algos are able to correctly match different pictures of the same person and identify her!

Output

Machine Learning has revolutionized the ways in which businesses relate to their customers. When we post a question on Stack Overflow it is the Machine learning who predicts the tags to that questions based on its title and description. When you push “like” on a Facebook post your feed is adjusted to contain more content like that in the future. This is Machine Learning. When you buy something on Amazon — say a camera, and it recommends that you also buy the accompanying camera case and the batteries for that camera, this is Amazon’s recommendation engine at work.where it is a medical field or where it is stock market Machine learning is everywhere now a day.

Thanks for reading