First of all, let us start with the Definition and basic intuition of the concept of Machine Learning!
Machine Learning is a subset of Scientific Computing, where problems that are almost impossible to solve manually by a human are solved with ease.
Machine Learning is a very vast field and one certainly cannot master it completely. It consists mainly of
- Data Structures
- Data Preprocessing
- Mathematics and Vector operations
- Deep Learning
Confusing right? let me break it down for you.
- Algorithms, Algorithms are basically a sequence or a set of rules given to a computer to perform a task or other such problem solving topics. examples of Algorithms are Binary Search Tree, Sorting Algorithm etc.
- Data Structures, Data Structures deal with the storing of Data on a computer according to the kind of work you are going to perform on the data. Examples of Data Structures are Queue, Hashmap, Linked List, Stacks etc.
- Data Preprocessing. Basically Data Preprocessing is a topic that has been derived from Data mining, It is the process of converting real life data which is often incomplete, inconsistent and lacking into data that is understandable. This has proven to be the best method for dealing with incomplete or lacking forms of Data.
- Statistics, Analytics. This topic focuses on the way to work with the data by using Statistical Analysis and general Analysis of the data.
- Mathematics and Vector Operations, Mathematics is the beating heart of Computer Science. Under the hood, machine learning is just performing vector calculations and manipulating Matrices . This just proves to say that math is embedded everywhere! Information is processed in the form of Vectors or Numpy arrays.
- Deep learning. This is a subset of Machine Learning which unlocks a lot of hidden possibilities in the field of ML. Deep learning models have outperformed any other type of Machine Learning model pretty much every time! The intuition behind this is that we can make the computer understand certain patterns by itself ( learning ) on the Data by looking at thousands of examples. We just specify the input and the output while training, the model itself understands the connections that it needs to make. In a way this mimics the Human Brain. The way in which the model learns will be discussed in a future blog.
- Visualization. We give the input to the model and get the output after performing some steps but often the results aren’t in Human readable format. This issue gets cleared with Visualization. The intuition behind Visualization is to make the output more human friendly!
So according to me these are the main things that you need to know before diving into the world of Machine learning!
Now as we know the concepts that contribute to Machine Learning let us see what it actually means.
- Machine learning is a field of computer science that uses statistical techniques to give computer systems the ability to learn with data, without being explicitly programmed. This means that we do not have to Hard-code every single aspect and feature. During the training phase we just, Provide the input and desired output and the model maps the connections between them by learning through many examples.
So by now you guys should have got a good understanding about the concepts and core fundamentals about Machine Learning.
Now lets ask the question – Why is machine learning necessary?
Machine Learning helps us a lot when we have an abstract idea and no real way of implementing it in code! We can specify our input and the desired output based on that particular input while training and the model understands by itself. Another major advantage is that Machine Learning when used correctly, can perform tasks with a lot of precision that normal code just cant do!
Of course there are many more answers to this question and this will be a subject for the next blog where we discuss about the necessity and implementations of Machine Learning.
Hope you guys learnt something new and found some valuable information! Thank you guys it has been a pleasure to speak about this topic. See you soon!