Hello Folks,
We have been hearing a lot about Artificial Intelligence and how it has been influencing our day to day life for over a few decades. In this post I would like to give a small introduction to ML and the types of it. This post is for those who are interested in ML application and who want to get into the field of Machine Learning.
When we tag a face on a social media photo, it is AI that is running behind the scenes and identifying faces in a picture. Face tagging is now omnipresent in several applications that display pictures with human faces. It is not limited to human faces there are several application that detects cats, dogs, bottles, cars, etc.
The latest feature, autonomous cars that detect objects in real time to steer the car. When you travel, you use Google Directions to learn the real-time traffic situations and follow the best path suggested by Google at that point of time. This is yet another implementation of object detection technique in real time.
Each one of us use AI in many parts of our lives, even without our knowledge. Today’s AI can perform extremely complex jobs with a great accuracy and speed. One such example is, We all use Google Directions during our trip anywhere in the city for a daily commute or even for inter-city travels. Google Directions application suggests the fastest path to our destination at that time instance. When we follow this path, we have observed that Google is almost 100% right in its suggestions and we save our valuable time on the trip.
Most of the Tradition techniques are still in use today due to the expertise and the accuracy which can be achieved with these algorithms.
Today the amount of data available is abundant. To analyze the kind of huge data that we possess statistical techniques are of not much help as they have some limitations of their own. More advanced methods such as deep learning are hence developed to solve many complex problems.
It is similar to training a child on how to ride a bike. You support the child until the child learns how bike on its own. You may support it with side wheels or u hold the seat until the child can balance itself, but once the child learns how to ride the bike its on its own. This is how Supervised learning works you teach the algorithm what to identify or what to search for. This is part of training, Once the algorithm is trained and tested, then it is ready to handle real world data.
In this case we give concrete known examples to the computer. For a given feature value x1 the output is y1, for x2 it is y2, for x3 it is y3, and so on. Based on this data, you let the computer figure out an empirical relationship between x and y. Once the machine is trained in this way with a sufficient number of data points, now you would ask the machine to predict Y for a given X.
In classification we classify objects of similar nature into a group or multiple group. For example, in a set of 1000 students say, you may like to group them into different groups based on their heights. Measuring the height of each student, you will place them in a proper group. Now, when a new student comes in, you will put him in an appropriate group by measuring his height.
Imagine you are in a foreign country and you are visiting a food market. You see a stall selling a fruit that you cannot identify. You don’t know the name of this fruit. However, you have your observations to rely on, and you can use these as a reference. In this case, you can easily the fruit apart from nearby vegetables or other food by identifying its various features like its shape, color, or size. In unsupervised learning, we do not specify a target to the machine, rather we ask machine “What can you tell me about X?”.
In clustering, we ask questions such as given a huge data set , “What are the five best groups we can make out of the datasets?” or “What features occur together most frequently in data?”. To answer such questions, the machine would require to deduce a strategy which would be very large and cluster it.
Consider training a pet dog, we train our pet to bring a ball to us. We throw the ball at a certain distance and ask the dog to fetch it back to us. Every time the dog does this right, we reward the dog. Slowly, the dog learns that doing the job rightly gives him a reward and then the dog starts doing the job right way every time in future. Exactly, this concept is applied in “Reinforcement” type of learning.
The deep learning is a model based on Artificial Neural Networks (ANN), more specifically Convolutional Neural Networks (CNN)s. There are several architectures used in deep learning such as deep neural networks, deep belief networks, recurrent neural networks, and convolutional neural networks.
The Deep Reinforcement Learning (DRL) combines the techniques of both deep and reinforcement learning. The reinforcement learning algorithms like Q-learning are now combined with deep learning to create a powerful DRL model. The technique has been with a great success in the fields of robotics, video games, finance and healthcare. Many previously unsolvable problems are now solved by creating DRL models. There is lots of research going on in this area and this is very actively pursued by the industries.
So far, I have briefly introduced various machine learning models, in my next post i will write more about individual learning techniques.
**image source - https://www.google.com/url?sa=i&url=https%3A%2F%2Fwww.forbes.com%2Fsites%2Ftomtaulli%2F2019%2F03%2F02%2Fwhat-you-need-to-know-about-machine-learning%2F&psig=AOvVaw0YieMVOYUHrg1J4sz5-cs7&ust=1612806451312000&source=images&cd=vfe&ved=0CAIQjRxqFwoTCKCAtMuq2O4CFQAAAAAdAAAAABAD, TutorialsPoint
