TensorFlow Certification Training (41 Blogs) Become a Certified Professional
AWS Global Infrastructure

Artificial Intelligence

Topics Covered
  • Machine Learning with Mahout (7 Blogs)
  • TensorFlow Certification Training (39 Blogs)
  • Artificial Intelligence and Machine Learning (19 Blogs)

What Is A Neural Network? Introduction To Artificial Neural Networks

Published on Aug 28,2019 2.8K Views
Zulaikha Lateef
Zulaikha is a tech enthusiast working as a Research Analyst at Edureka. Zulaikha is a tech enthusiast working as a Research Analyst at Edureka.

With the advancement in Machine Learning, Artificial Intelligence has taken a high road. Deep Learning is considered to be the most advanced technology built to solve complex problems that use massive data sets. This blog on what is a Neural Networks will introduce you to the basic concepts of Neural Networks and how they can solve complex data-driven problems.

To get in-depth knowledge of Artificial Intelligence and Deep Learning, you can enroll for live Deep Learning with TensorFlow Training by Edureka with 24/7 support and lifetime access.

Here’s a list of topics that will be covered in this blog:

  1. What is a Neural Network?
  2. What is Deep Learning?
  3. Difference Between AI, ML and, DL
  4. Need For Deep Learning
  5. Deep Learning Use Case
  6. How Neural Networks work?
  7. Neural Network Explained With Example

Simple Definition Of A Neural Network

Modeled in accordance with the human brain, a Neural Network was built to mimic the functionality of a human brain. The human brain is a neural network made up of multiple neurons, similarly, an Artificial Neural Network (ANN) is made up of multiple perceptrons (explained later).

Neural Network - What Is A Neural Network - Edureka

A neural network consists of three important layers:

  • Input Layer: As the name suggests, this layer accepts all the inputs provided by the programmer.
  • Hidden Layer: Between the input and the output layer is a set of layers known as Hidden layers. In this layer, computations are performed which result in the output.
  • Output Layer: The inputs go through a series of transformations via the hidden layer which finally results in the output that is delivered via this layer.

Before we get into the depths of how a Neural Network functions, let’s understand what Deep Learning is.

What Is Deep Learning?

Deep Learning is an advanced field of Machine Learning that uses the concepts of Neural Networks to solve highly-computational use cases that involve the analysis of multi-dimensional data. It automates the process of feature extraction, making sure that very minimal human intervention is needed.

Deep Learning - What Is A Neural Network - Edureka

So what exactly is Deep Learning?

Deep Learning is an advanced sub-field of Machine Learning that uses algorithms inspired by the structure and function of the brain called Artificial Neural Networks.

Difference Between AI, ML, and DL (Artificial Intelligence vs Machine Learning vs Deep Learning)

People often tend to think that Artificial Intelligence, Machine Learning, and Deep Learning are the same since they have common applications. For example, Siri is an application of AI, Machine learning and Deep learning.

AI vs ML vs DL - What Is A Neural Network - Edureka

So how are these technologies related?

  • Artificial Intelligence is the science of getting machines to mimic the behavior of humans.
  • Machine learning is a subset of Artificial Intelligence (AI) that focuses on getting machines to make decisions by feeding them data.
  • Deep learning is a subset of Machine Learning that uses the concept of neural networks to solve complex problems.

To sum it up AI, Machine Learning and Deep Learning are interconnected fields. Machine Learning and Deep learning aids Artificial Intelligence by providing a set of algorithms and neural networks to solve data-driven problems.

Now that you’re familiar with the basics, let’s understand what led to the need for Deep Learning.

Need For Deep Learning: Limitations Of Traditional Machine Learning Algorithms and Techniques

Machine Learning was a major breakthrough in the technical world, it led to the automation of monotonous and time-consuming tasks, it helped in solving complex problems and making smarter decisions. However, there were a few drawbacks in Machine learning that led to the emergence of Deep Learning.

Need For Deep Learning - What Is A Neural Network - Edureka

Here are some limitations of Machine Learning:

  1. Unable to process high dimensional data: Machine Learning can process only small dimensions of data that contain a small set of variables. If you want to analyze data containing 100s of variables, then Machine Learning cannot be used.
  2. Feature engineering is manual: Consider a use case where you have 100 predictor variables and you need to narrow down only the significant ones. To do this you have to manually study the relationship between each of the variables and figure out which ones are important in predicting the output. This task is extremely tedious and time-consuming for a developer.
  3. Not ideal for performing object detection and image processing: Since object detection requires high-dimensional data, Machine Learning cannot be used to process image data sets, it is only ideal for data sets with a restricted number of features.

Before we get into the depths of Neural Networks, let’s consider a real-world use case where Deep Learning is implemented.

Deep Learning Use Case/ Applications

Did you know that PayPal processes over $235 billion in payments from four billion transactions by its more than 170 million customers? It uses this vast amount of data to identify possible fraudulent activities among other reasons.

With the help of Deep Learning algorithms, PayPal mined data from their customer’s purchasing history in addition to reviewing patterns of likely fraud stored in its databases to predict whether a particular transaction is fraudulent or not.

Deep Learning Use Case - Artificial Intelligence With Python - Edureka

The company has been relying on Deep Learning & Machine Learning technology for around 10 years. Initially, the fraud monitoring team used simple, linear models. But over the years the company switched to a more advanced Machine Learning technology called, Deep Learning.

Fraud risk manager and Data Scientist at PayPal, Ke Wang, quoted:

“What we enjoy from more modern, advanced machine learning is its ability to consume a lot more data, handle layers and layers of abstraction and be able to ‘see’ things that a simpler technology would not be able to see, even human beings might not be able to see.”

A simple linear model is capable of consuming around 20 variables. However, with Deep Learning technology one can run thousands of data points. Therefore, by implementing Deep Learning technology, PayPal can finally analyze millions of transactions to identify any fraudulent activity.

Now let’s go into the depths of a Neural Network and understand how they work.

How Does A Neural Network Work?

To understand neural networks, we need to break it down and understand the most basic unit of a Neural Network, i.e. a Perceptron.

What Is A Perceptron?

A Perceptron is a single layer neural network that is used to classify linear data. It has 4 important components:

  1. Inputs
  2. Weights and Bias
  3. Summation Function
  4. Activation or transformation Function

Concepts of A Neural Network - What Is A Neural Network - Edureka

The basic logic behind a Perceptron is as follows:

The inputs (x) received from the input layer are multiplied with their assigned weights w.  The multiplied values are then added to form the Weighted Sum. The weighted sum of the inputs and their respective weights are then applied to a relevant Activation Function. The activation function maps the input to the respective output.

Weights and Bias In Deep Learning

Why do we have to assign weights to each input?

Once an input variable is fed to the network, a randomly chosen value is assigned as the weight of that input. The weight of each input data point indicates how important that input is in predicting the outcome.

The bias parameter, on the other hand, allows you to adjust the activation function curve in such a way that a precise output is achieved.

Summation Function

Once the inputs are assigned some weight, the product of the respective input and weight is taken. Adding all these products gives us the Weighted Sum. This is done by the summation function.

Activation Function

The main aim of the activation functions is to map the weighted sum to the output. Activation functions such as tanh, ReLU, sigmoid and so on are examples of transformation functions.

To learn more about the functions of Perceptrons, you can go through this Deep Learning: Perceptron Learning Algorithm blog.

Before we wrap up this blog, let’s take a simple example to understand how a Neural Network operates.

Neural Networks Explained With An Example

Consider a scenario where you are to build an Artificial Neural Network (ANN) that classifies images into two classes:

  • Class A: Containing images of non-diseased leaves
  • Class B: Containing images of diseased leaves

So how do you create a Neural network that classifies the leaves into diseased and non-diseased crops?

The process always begins with processing and transforming the input in such a way that it can be easily processed. In our case, each leaf image will be broken down into pixels depending on the dimension of the image.

For example, if the image is composed of 30 by 30 pixels, then the total number of pixels will be 900. These pixels are represented as matrices, which are then fed into the input layer of the Neural Network.

Neural Network Example - What Is A Neural Network - Edureka

Just like how our brains have neurons that help in building and connecting thoughts, an ANN has perceptrons that accept inputs and process them by passing them on from the input layer to the hidden and finally the output layer.

As the input is passed from the input layer to the hidden layer, an initial random weight is assigned to each input. The inputs are then multiplied with their corresponding weights and their sum is sent as input to the next hidden layer.

Here, a numerical value called bias is assigned to each perceptron, which is associated with the weightage of each input. Further, each perceptron is passed through activation or a transformation function that determines whether a particular perceptron gets activated or not.

An activated perceptron is used to transmit data to the next layer. In this manner, the data is propagated (Forward propagation) through the neural network until the perceptrons reach the output layer.

At the output layer, a probability is derived which decides whether the data belongs to class A or class B.

Sounds simple, doesn’t it? Well, the concept behind Neural Networks is purely based on the functioning of the human brain. You require in-depth knowledge of various mathematical concepts and algorithms. Here’s a list of blogs to get you started:

  1. What is Deep Learning? Getting Started With Deep Learning
  2. Deep Learning with Python: Beginners Guide to Deep Learning
  3. Neural Network Tutorial – Multi Layer Perceptron
  4. Backpropagation – Algorithm For Training A Neural Network

If you found this blog relevant, check out the Deep Learning with TensorFlow Training by Edureka, a trusted online learning company with a network of more than 250,000 satisfied learners spread across the globe. The Edureka Deep Learning with TensorFlow Certification Training course helps learners become expert in training and optimizing basic and convolutional neural networks using real-time projects and assignments along with concepts such as SoftMax function, Auto-encoder Neural Networks, Restricted Boltzmann Machine (RBM).


Join the discussion

Browse Categories

webinar_success Thank you for registering Join Edureka Meetup community for 100+ Free Webinars each month JOIN MEETUP GROUP

Subscribe to our Newsletter, and get personalized recommendations.