Machine Learning is broadly categorized under the following headings −
Source: https://www.tutorialspoint.com/machine_learning/machine_learning_categories.htm
Machine learning evolved from Supervised to Deep reinforcement learning as shown in the above diagram. Initially, researchers started out with Supervised Learning. This is the case of housing price prediction discussed earlier. This was followed by unsupervised learning, where the machine is made to learn on its own without any supervision and this is without a label.
It is always good to appreciate the work so Scientists discovered further that it may be a good idea to reward or acknowledge the machine when it does the job the expected way and then there came the Reinforcement Learning.
Very soon, the data that is available these days has become so humongous that the conventional techniques developed so far failed to analyze the big data and provide us with the predictions. Thus came the deep learning where the human brain is simulated in the Artificial Neural Networks (ANN) created in our binary computers.
The machine now learns on its own using the high computing power and huge memory resources that are available today. It is now observed that Deep Learning has solved many of the previously unsolvable problems.
The technique is now further advanced by giving incentives to Deep Learning networks as awards and there finally comes Deep Reinforcement Learning.
Classifications in Machine learning
Supervised Learning
Supervised learning is analogous to training a child to walk. You will hold the child’s hand, show him how to take his foot forward, walk yourself for a demonstration and so on, until the child learns to walk on his own.
1. Regression
Regression algorithms are used if there is a relationship between the input variable and the output variable. It is used for the prediction of continuous variables. Below are some popular Regression algorithms which come under supervised learning:
- Linear Regression
- Regression Trees
- Non-Linear Regression
- Bayesian Linear Regression
- Polynomial Regression
2. Classification
Classification algorithms are used when the output variable is categorical, which means there are two class such as Yes/No,true/False etc,
Spam Filtering,
2. Unsupervised Learning
In unsupervised learning, the target data is not specified, rather we ask machine “What can you tell me about X?”. More specifically, we may ask questions such as given a huge data set X, “What are the three best groups we can make out of X?” or “What features occur together most frequently i.e. mode in X?”. To arrive at the answers to such questions, you can understand that the number of data points that the machine would require to deduce a strategy would be very large.
In case of supervised learning, the machine can be trained with even about a few thousands of data points. However, in case of unsupervised learning, the number of data points that you may think is reasonable and accepted for learning which starts in a few millions. These days, the data is generally abundantly available. The data ideally requires curating. However, the amount of data that is continuously flowing in a social area network i.e. social websites, in most cases data curation is an impossible task.
The following figure shows the boundary between the yellow and red dots as determined by unsupervised machine learning. You can see it clearly that the machine would be able to determine the class of each of the black dots with a fairly good accuracy.
Source:
https://chrisjmccormick.files.wordpress.com/2013/08/approx_decision_boun dary.png
The unsupervised learning has shown a great success in many modern AI applications, such as face detection, object detection, and so on.
3. Reinforcement Learning
Consider training a pet cat, we train our pet to bring a object to us. We throw the object at a certain distance and ask the cat to fetch it back to us. Every time the cat does this right, we reward the cat. Slowly, the cat learns that doing the job rightly gives him a reward and then the cat starts doing the job right way every time in future. Exactly, this concept is applies in “Reinforcement” type of learning. The technique was initially develop for machines to play games.
The machine provides an algorithm to analyze all possible moves at each stage of the game. The machine may select random moves. based on the move If the move is right, the machine is reward by, otherwise it may be penalized. Slowly, the machine will start differentiating between right and wrong moves and after several iterations will learn to solve the game puzzle with better accuracy. The accuracy of winning the game would improve as the machine plays more and more games.
The entire process may be depicted in the following diagram −
This technique of machine learning differs from the supervised learning in that you need not supply the labelled input/output pairs. The focus is on finding the balance between exploring the new solutions versus exploiting the learned solutions.
4. Deep Learning
Deep learning is a model based on Artificial Neural Networks (ANN), more specifically Convolutional Neural Networks (CNN)s. There are various architectures use in deep learning such as deep neural networks, recurrent neural networks, deep belief networks and convolutional neural networks.
These networks have been successfully applies in solving the problems of computer vision, speech recognition, natural language processing, bioinformatics, drug design, medical image analysis, Virtual assistants, vision for driverless cars, money laundering, face recognition and games. There are several other fields in which deep learning is proactively apply upon. Deep learning requires huge processing power and humongous data, which is generally easily available these days.
5. Deep Reinforcement Learning
The Deep Reinforcement Learning (DRL) combines the techniques of both deep and reinforcement learning. The algorithms like Q-learning now combines with deep learning to create a powerful DRL model. The technique has been a great success in the fields of robotics, video games, finance and healthcare. Many previously not solvable problems are now solved by creating DRL models. yet there is continuous research going to make it better day by day
So far, you have got a brief introduction to various machine learning models. now let us explore slightly deeper into various algorithms that are available under these models.
written by: Nikesh Maurya
Reviewed By: Krishna Heroor
If you are Interested In Machine Learning You Can Check Machine Learning Internship Program
Also Check Other Technical And Non Technical Internship Programs
