Skip to main content

INTRODUCTION TO DEEP LEARNING - Neural Networks




What is a neural network?

The term deep learning refers to training neural networks. In this post I’d like to provide some basic intuitions on neural networks.

    Let us consider an example where we are trying to predict the price of a house given its size. Let’s say we have a dataset with size of the houses and their corresponding price and we want to fit a function to predict the price of the house as a function of its size. In Linear Regression we try to draw a straight line to the available dataset.



    But we know that the straight line can eventually be negative whereas the price of a house is always greater than zero. So, we try to bend the curve so that it ends at 0. We can think of the function we just fit as a simple neural network where we have a node (neuron) with input as size of the house and output as price. The function is called RECTIFIED LINEAR UNIT (RELU).
                                
                               
                     
    A larger neural network can be formed by stacking all the single neurons. Let us extend the housing price example to understand more about this concept. Let’s say we want to predict the price of a house not just by its size but also with other features such as the number of bedrooms which implies that family size also helps in predicting the price of a house. We also have features like zip code (postal code) which determine walkability and wealth which determines the quality of facilities such as schools and colleges.


    Each of the circles (neurons) can be a RELU function or some other non-linear function. Most of the people tend to pay more looking at the things that matter to them. In this case the walkability, family size and quality of the schools can help predict the price precisely. In this example, ‘X’ is the four input features and Y is the output which is the price of a house.

    All we need to do is provide the neural network with the input ‘X’ and the output ‘Y’ while training the neural network with several training examples. The neural network will automatically identify all the middle layers by itself. Each of the neuron (circle) takes input of all the four input features. So instead of saying that the first node represents family size that family size depends only on the size of the house and the number of bedrooms, we give the neuron all the input features (x1, x2, x3, x4) and it should figure out whatever it wants the node to be.



     We say that the input layer and the hidden layer are densely connected because every input is connected to every one of these neurons(nodes).

 So, I hope I gave you a basic understanding of what a neural network is and is it used to make predictions. In the next post we will look at some more examples of neural networks and supervised learning.

Comments

Popular posts from this blog

What’s the difference between AngularJS, Angular2 and Angular4?

One question that often comes out is “What is the basic difference between AngularJS, Angular 2 and Angular 4 and how to jump from Angular 2 to Angular 4?”


Angular JS was introduced in 2010 as a JavaScript framework for building client side single page web applications. So it gained popularity and the Angular team at google started to add some more features to the core. But the framework was not designed with the needs of today’s applications in mind and moreover it was totally complex. So the Angular team decided to rewrite the entire framework using TYPESCRIPT and as a result Angular 2 was released in mid 2016. The new Angular framework is completely different from the previous version and we can think of it as a completely different framework compared to the earlier one.

The decision was frustrating to most of the developers since a lot of applications have been designed using AngularJS. I personally liked the direction that Angular developers took in rewriting the entire framework a…

ANGULAR-2

Angular JS is an open source framework built on JavaScript. It was built by the
developers at Google. This framework was used to overcome obstacles encountered while
working with Single Page applications. Also, testing was considered as a key aspect while
building the framework. It was ensured that the framework could be easily tested. The
initial release of the framework was in October 2010.

Features of Angular 2:Components: The earlier version of Angular had a focus of Controllers but now has changed the focus to having components over controllers. Components help to
build the applications into many modules. This helps in better maintaining the
application over a period of time.

TypeScript: The newer version of Angular is based on TypeScript. This is a
superset of JavaScript and is maintained by Microsoft.

Services: Services are a set of code that can be shared by different components
of an application. So for example, if you had a data component that picked data
from a database, you …