Cover image for Machine Learning - Introduction

Machine Learning - Introduction

sandeepbalachandran profile image Sandeep Balachandran ・3 min read

Hello there,
I am back with another series for myself. This is the very "new" topic lets say you have never heard of.

In this series i am gonna bring

  • TensorFlow JS
  • TensorFlow Lite
  • Colab

TensorFlow JS

TensorFlow.js is a JavaScript Library for training and deploying machine learning models in the browser and in Node.js.

TensorFlow Lite

TensorFlow Lite is a set of tools to help developers run TensorFlow models on mobile, embedded, and IoT devices. It enables on-device machine learning inference with low latency and a small binary size.


Colab is an interactive Python notebook which runs in Google Cloud.
That means you'll be able to do all the coding right here in your browser without needing to install anything on your computer. If you're familiar with Jupyter, you can view Colab as being a Jupyter Notebook server hosted in the Google Cloud.

When studying Machine Learning you will come across many different terms such as artificial intelligence, machine learning, neural network, and deep learning. But what do these terms actually mean and how do they relate to each other?

A brief description of these terms:

Artificial Intelligence:

A field of computer science that aims to make computers achieve human-style intelligence. There are many approaches to reaching this goal, including machine learning and deep learning.

Machine Learning:

A set of related techniques in which computers are trained to perform a particular task rather than by explicitly programming them.

Neural Network:

A construct in Machine Learning inspired by the network of neurons (nerve cells) in the biological brain. Neural networks are a fundamental part of deep learning, and will be covered in this course.

Deep Learning:

A subfield of machine learning that uses multi-layered neural networks. Often, “machine learning” and “deep learning” are used interchangeably.

Machine learning and deep learning also have many subfields, branches, and special techniques.

A notable example of this diversity is the separation of Supervised Learning and Unsupervised Learning.

To over simplify —
in supervised learning you know what you want to teach the computer,

while unsupervised learning is about letting the computer figure out what can be learned.

Applicatios of machine learning

  • Machine learning algorithms can now detect skin cancer just as accurate as board certified dermatologists.In this case, a deep neural network was trained on hundreds of thousands of skin cancer images and learned to recognize skin cancer from single images.
  • Self-driving cars.Thanks to machine learning,we can now develop autonomous vehicles that can drivethemselves using only the data from various sensors.
  • Games.Machine learning algorithms can be used to teach computers how to play games at a superhuman performance. For example, you might have heard about Go,where Google deep mind usedmachine learning algorithms to beat the best Go players in the world.

These are just a few examples of how machine learning is revolutionizing our world.Therefore, learning how to develop deep neural networks means that you are writing software that can potentially change the lives of people all over the world.

Posted on by:

sandeepbalachandran profile

Sandeep Balachandran


Very much interested in working with a space exploration team. Interested in human body anatomy. Currently a dev


Editor guide