The Machine Learning Blog

This is the third article in a series of three articles, explaining how to build an image classifier without coding. Click here to read part 1 and click here to read part 2.

This is the second article in a series of three articles, explaining how to build an image classifier without coding. If you have not read part 1, please read it here before continuing.

The present article corresponds to part 2 of the topic "Artificial Intelligence and Mathematics". For your understanding I recommend to review the first part beforehand.

Neural networks (DNN) are one of the most used machine learning models nowadays. DNN can be viewed as a set of nodes and lines forming a network. Its similarity with the organization of neurons in the brain is evident, but this topic will be discussed later.

I am a biologist and from my precarious corner of knowledge, but thanks to the close relationship with professionals from multiple disciplines, mostly linked to the Neuroscience Institute of the Universidad del Bosque, I have entered into the fascinating adventure of understanding the basics of Artificial Intelligence.

Recognizing hand written numbers

In this post, I will explain how to use Machine Learning to build a piece of software that is able to recognize handwritten numbers. I will also explain what other applications this could have for you and your business. This being said, I will not go into implementation details, nor into the mathematics of how this works, the post will just explain the general idea behind this principle.

Fear and admiration for AI

Ever since I was a kid, I was fascinated by Artificial Intelligence. I read almost all novels from my favorite author of all times, Isaac Asimov who came up with the three laws of robotics...

Machine Learning used to be really expensive

Once upon a time, if you wanted to implement a machine learning project, besides from an exploitable dataset, you also needed two things:

• An incredibly expensive salary (over $300K) to hire a ML expert, specialised in a particular field (deep learning, convolutional neural networks, etc)
• Huge and very expensive IT infrastructure, specially to do the parallel computing required to train ML models.

Both these elements made it impossible for normal companies to implement Machine Learning in their every day operations and ML was reserved to only the wealthiest corporations in the world.