My Overview of Machine Learning

If you are a tech guy, you’ll quickly notice that almost everything coming out of the technology world seems to have some element of Artificial Intelligence (AI) or Machine Learning (ML) to it. American computer scientist John McCarthy coined the term ‘Artificial Intelligence’ in 1956. The word AI refers to the ability of a machine to simulate intelligent human behavior. AI is being utilized broadly in medical diagnosis, electronic trading platforms, robot control, and remote sensing.

Though people have a huge hype in this, they often mistakenly use AI and ML as synonyms. Machine Learning is a subset of AI. And AI is wider area.

AI vs ML vs DL
[src: https://www.argility.com/argility-ecosystem-solutions/iot/machine-learning-deep-learning/]

Before we discuss machine learning in details, let’s talk about algorithms. An algorithm is a set of rules to solve a problem. It is a step-by-step demonstration for processing data. Machine learning refers to training an algorithm by a large amount of data, which can effectively solve some problems like face detection, image classification, email spam, and malware filtering, etc.

An Example

Suppose, a machine is said to detect cats and dogs. Here the machine is built, through a computer program. So, at first, this program is like a newborn child. It does not know anything about cats and dogs until it gets to learn how dogs and cats look in real or in image

dog and cat
[src: https://storage.googleapis.com/petbacker/images/blog/2017/dog-and-cat-cover.jpg]

So, how can we teach the program about cat and dog! It’s the time when ML comes into play. ML has many popular algorithms such as Support Vector Machines, Decision Trees, Random Forest, Neural Networks, etc. which can help a machine to learn. The whole process works as follows-

  • Data Collection: For this domain problem, let’s download the dogs and cats images from Kaggle (a renowned platform for ML enthusiasts). There are two types of images, a) train and b) test
  • Features: Collect features from these images such as colors, edges, etc
  • Model: Select an algorithm which can be suitable for your data. There is no optimized idea to choose a better algorithm. It depends on your data. So try them one by one.
  • Train Model: Train your program using train images features
  • Evaluate Model: At last, test your model against the test data
  • Results: Go through all algorithms and get the accuracy
  • Best Model: Finally, choose the best model which is perfect in terms of effectiveness and accuracy

In this blog post, I have tried to give an overall idea of Machine Learning. Hope it may help you.

Happy learning, Happy coding!

Software Engineer | Professional Scrum Master | Research Enthusiast

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store