If you've read my previous articles, you'll know what's coming next. In this part of the Internet, we take concepts that seem complex and make them fun and novel by illustrating them. And if you haven't read my previous articles, I recommend that you start with my series of articles covering the machine learning basics because you will find that much of the material covered there is relevant here.
Today we're going to tackle the big topic: an introduction to neural networks, a type of machine learning model. This is just the first article in a whole series I plan to write on deep learning. It will focus on how a simple artificial neural network learns and provide you with a deep (ha, pun intended) understanding how a neural network is built, neuron by neuron, which is super essential as we will continue to build on this knowledge. While we'll delve into the mathematical details, there's no need to worry because we'll break down and illustrate each step. At the end of this article, you will realize that it is much simpler than it seems.
But before exploring that, you might be wondering: Why do we need neural networks? With so many machine learning algorithms available, why choose neural networks? The answers to this question are abundant and widely discussed, so we won't go too deep into it. But it's worth noting that neural networks are incredibly powerful. They can identify complex patterns in data that classical algorithms may struggle with, address highly complex machine learning problems (such as natural language processing and image recognition), and decrease the need for extensive feature engineering and manual efforts. .
But with all that said, neural network problems pretty much boil down to 2 main categories: Classification, which predicts a discrete label for a given input (e.g., is this a picture of a cat or a dog? The review of is this movie positive or negative?) or Regression, which predicts a continuous value for a given input (e.g. weather prediction).
Today we will focus on a regression problem. Consider a simple scenario: We recently moved to a new city and are currently looking for a new home. However, we noticed that home prices in the area vary significantly.
Since we are not familiar with the city, our only source of information is what…
