Machine Learning For Absolute Beginners
Machines are learning, when will you?
In recent times, we hear these few things a lot:
First is —The COVID-19 Pandemic, of course!
Second is — Quarantine and the Third is “Machine Learning’’. Yes, Machine Learning is so much in hype these days and no doubt that it is a technology of the future. Machine Learning, Artificial Intelligence, Data Science, etc are the pioneers of futuristic applications. Thus, in this article, we’ll talk about Machine Learning: What it is, How it works, at the beginner level!
So let’s start.
So first, let’s look into What is Machine Learning?
Machine Learning is a subset of Artificial Intelligence and is defined as,
“The study of computer algorithms that improve automatically through experience”
Before we move ahead, let’s see how Tom Mitchell defines Machine Learning:
“A well-posed learning problem is defined as, A computer program is said to learn from experience E with respect to some task T and some performance measure P if its performance on T as measured by P improves with experience E ”
Ok, I know, both the definitions might sound a bit overwhelming at the moment. Thus let’s see in simple terms how it works so that you will be able to appreciate their definitions. So in simple terms, what is a Machine Learning Algorithm?
It’s like a child’s brain. When the kid is young you show him/her an Apple and tell that this is Apple. If you repeat this a few times, it establishes a connection with the child’s brain in order to recognize an Apple.
Suppose, next time the kid see’s an Apple he might be able to recognize an apple using its features such as color, size, shape, category, etc.
Now, when we talk about machine learning, replace the child’s brain by a machine learning model, and replace the apple with some data.
Thus, this is Machine Learning at a very basic level and this is how it works. Now, once you read the above definitions again, this time you would surely be able to understand and appreciate them.
Now that we know that what is Machine Learning and how it works, let’s look at the steps in Machine Learning:
- Data Collection
- Data Preparation
- Choosing a Model
- Training a Model
- Evaluating a Model
- Parameter tuning
- Implementation
Thus, for a machine learning model, Data is an important aspect. From data collection to preparation for choosing and training the model makes machine learning algorithms.
Thus, let’s talk about the types of machine learning algorithms. At the most basic level, there are three types of learning:
1) Supervised Learning
Supervised learning as the name indicates the presence of a supervisor as a teacher. Basically supervised learning is a learning in which we teach or train the machine using data that is well labeled which means some data is already tagged with the correct answer. After that, the machine is provided with a new set of examples (data) so that the supervised learning algorithm analyses the training data (set of training examples) and produces a correct outcome from labeled data.
2) Unsupervised Learning
Unsupervised learning is the training of machines using information that is neither classified nor labeled and allowing the algorithm to act on that information without guidance. Here the task of the machine is to group unsorted information according to similarities, patterns, and differences without any prior training of data.
Unlike supervised learning, no teacher is provided, which means no training will be given to the machine. Therefore the machine is restricted to find the hidden structure in unlabeled data by ourselves.
3) Reinforcement Learning
Reinforcement learning is an area of Machine Learning. It is about taking suitable action to maximize reward in a particular situation. It is employed by various software and machines to find the best possible behavior or path it should take in a specific situation.
Reinforcement learning differs from the supervised learning in a way that in supervised learning the training data has the answer key with it so the model is trained with the correct answer itself, whereas in reinforcement learning, there is no answer but the reinforcement agent decides what to do to perform the given task. In the absence of a training dataset, it is bound to learn from its experience.
This is all about Machine Learning that you should know to get started with it.
What are your thoughts on machine learning and is it overhyped? Curious to know in the comments…
