DEV Community

Cover image for NEURAL NETWORK
felix715
felix715

Posted on

NEURAL NETWORK

Neural Network Introduction

In this article, we will be talking about neural networks. A functional unit of deep learning, this means a neural network accepts input and gives an output. Deep Learning uses Artificial Neural Networks (ANN). ANNs imitates the human brain’s behavior to solve complex data problems.

Application

These technologies solve problems in image recognition, speech recognition, pattern recognition, and natural language processing (NLP), to name a few.

The Neural Network Overview

Have you ever wondered how your brain recognizes images? No matter what or how the image looks, the brain can tell that this is an image of a cat and not a dog. The brain relates to the best possible pattern and concludes the result. The example below will help you understand neural networks:
Consider a scenario where you have a set of labeled images, and you have to classify the images based on if it is a dog or a cat. To create a neural network that recognizes images of cats and dogs. The network starts by processing the input. Each image is made of pixels. For example, the image dimensions might be 20 X 20 pixels that make 400 pixels. Those 400 pixels would make the first layer of our neural network.

Image description
A neural network is made of artificial neurons that receive and process input data. Data is passed through the input layer, the hidden layer, and the output layer.A neural network process starts when input data is fed to it. Data is then processed via its layers to provide the desired output. A neural network learns from structured data and exhibits the output. Learning taking place within neural networks can be in three different categories:
Supervised Learning - with the help of labeled data, inputs, and outputs are fed to the algorithms. They then predict the desired result after being trained on how to interpret data.
Unsupervised Learning - ANN learns with no human intervention. There is no labeled data, and output is determined according to patterns identified within the output data.
Reinforcement Learning - the network learns depending on the feedback you give it.
The essential building block of a neural network is a perceptron or neuron. It uses the supervised learning method to learn and classify data. We will learn more about the perceptron later in this article.

How Neural Networks work

Neural Networks are complex systems with artificial neurons.
Artificial neurons or perceptron consist of:
Input
Weight
Bias
Activation Function
Output

Image description
The neurons receive many inputs and process a single output. Neural networks are composed of layers of neurons. These layers consist of the following:
Input layer
Multiple hidden layers
Output layer
The input layer receives data represented by a numeric value. Hidden layers perform the most computations required by the network. Finally, the output layer predicts the output.
In a neural network, neurons dominate one another. Each layer is made of neurons. Once the input layer receives data, it is redirected to the hidden layer. Each input is assigned with weights.
The weight is a value in a neural network that converts input data within the network’s hidden layers. Weights work by input layer, taking input data, and multiplying it by the weight value.
It then initiates a value for the first hidden layer. The hidden layers transform the input data and pass it to the other layer. The output layer produces the desired output.
The inputs and weights are multiplied, and their sum is sent to neurons in the hidden layer. Bias is applied to each neuron. Each neuron adds the inputs it receives to get the sum. This value then transits through the activation function.
The activation function outcome then decides if a neuron is activated or not. An activated neuron transfers information into the other layers. With this approach, the data gets generated in the network until the neuron reaches the output layer.
Another name for this is forward propagation. Feed-forward propagation is the process of inputting data into an input node and getting the output through the output node. (We’ll discuss feed-forward propagation a bit more in the section below).
Feed-forward propagation takes place when the hidden layer accepts the input data. Processes it as per the activation function and passes it to the output. The neuron in the output layer with the highest probability then projects the result.
If the output is wrong, backpropagation takes place. While designing a neural network, weights are initialized to each input. Backpropagation means re-adjusting each input’s weights to minimize the errors, thus resulting in a more accurate output.

Types of Neural Networks

Neural networks are identified based on mathematical performance and principles to determine the output. Below we will go over different types of neural networks.

Perceptron

Minsky and Papert (https://www.researchgate.net/publication/3081582_Review_of_'Perceptrons_An_Introduction_to_Computational_Geometry'_Minsky_M_and_Papert_S_1969) proposed the Perceptron model (Single-layer neural network). They said it was modeled after how the human brain functions.
It is one of the simplest models that can learn and solve complex data problems using neural networks. Perceptron is also called an artificial neuron.
A perceptron network is comprised of two layers:
Input Layer (https://www.techopedia.com/definition/33262/input-layer-neural-networks)
Output Layer (https://www.techopedia.com/definition/33263/output-layer-neural-networks)
The input layer computes the weighted input for every node. The activation function is used to get the result as output.

Image description

Feed Forward Neural Network

In a feed-forward network, data moves in a single direction. It enters via the input nodes and leaves through output nodes.This is a front propagation wave.
By moving data in one direction, there is no backpropagation. The backpropagation algorithm calculates the gradient of the loss function with consideration to weights in the network. The input product sum and their weights are computed. The data later is transferred to the output. A couple of feed-forward neural networks applications are:
Speech Recognition
Facial Recognition

Image description
Radial Basis Function Neural Network
Radial Basis Function Neural Networks (RBF are comprised of three layers:
Input Layer
Hidden Layer
Output Layer
RBF networks classify data based on the distance of any centered point and interpolation. Interpolation resizes images. Classification is executed by estimating the input data where each neuron reserves the data. RBF networks look for similar data points and group them. RBF networks classify data based on the distance of any centered point and interpolation. Interpolation resizes images. Classification is executed by estimating the input data where each neuron reserves the data. RBF networks look for similar data points and group them. According to Dr. Saed Sayad, the sum and weights of hidden layer output sent to the output layer form a network of outputs.

Image description

Recurrent Neural Network

Neural networks such as a feed-forward networks move data in one direction. This type of network has the disadvantage of not remembering the data in past inputs. This is where RNNs comes into play. RNNs do not work like standard neural networks. A Recurrent Neural Network (RNN) is a network good at modeling sequential data. Sequential data means data that follow a particular order in that a thing follows another. In RNN, the output of the previous stage goes back in as an input of the current step. RNN is a feedback neural network. Saving the output helps make other decisions.
In RNNs, data runs through a loop, such that each node remembers data in the previous step. For example: Let’s say you are taking five classes this semester, and this is your schedule: Monday = Cryptography, Tuesday = Audit of Information Systems, Wednesday = Advanced Database, Thursday = Java, and Friday = Business intelligence. For the NN to tell you the class you are studying (any given day), it has to be able to “look” at the class studied the day before.
With the example above, you can tell the output must go back in as input to decide the next output.RNNs have a memory that helps the network recall what happened earlier in the sequence data. While carrying out operations, neurons also act as memory cells.

Image description
RNN are used to solve problems in stock predictions, text data, and audio data. In other words, it’s used to solve similar problems in text-to-speech conversion and language translation. Learn more about text generation with RNN

Convolution Neural Network

Convolutional Neural Networks (CNN) are commonly used for image recognition. CNNs contain three-dimensional neuron arrangement. The first stage is the convolutional layer. Neurons in a convolutional layer only process information from a small part of the visual field (image). Input features in convolution are abstracted in batches.
The second stage is pooling. It reduces the dimensions of the features and, at the same time, sustains valuable data. CNNs launch into the third phase (fully connected neural network) when the features get to the right granularity level.
At the final stage, the final probabilities are analyzed and decide which class the image belongs to.This type of network understands the image in parts. It also computes the operations multiple times to complete the processing of the image.Image processing involves conversion from RGB to a grey-scale. After the image is processed, modifications in pixel value aid in identifying the edges. The images also get grouped into different classes. CNN is mainly used in signal and image processing. An article that may help shed some light on how general computer vision worK.

Image description

Modular Neural Network

A Modular Neural Network (MNN) is composed of unassociated networks working individually to get the output. The various neural networks do not interact with each other. Each network has a unique set of inputs compared to other networks.
MNN is advantageous because large and complex computational processes are done faster. Processes are broken down into independent components, thus increasing the computational speed.

Image description

Applications of Neural Networks

Neural networks are effectively applied to several fields to resolve data issues, some examples are listed below.

Facial Recognition

Neural networks are playing a significant role in facial recognition. Some smartphones can identify the age of a person. This is based on facial features and visual pattern recognition.

Weather Forecasting

Neural networks are trained to recognize the patterns and identify distinct kinds of weather. Weather forecasting, with the help of neural networks, not only predicts the weather.

Music composition

Neural networks are mastering patterns in sounds and tunes. These networks train themselves adequately to create new music. They are also being used in music composition software.

Image processing and Character recognition

Neural networks can recognize and learn patterns in an image. Image processing is a growing field.

Image recognition is used in:

Facial recognition.
Cancer cell detection.
Satellite imagery processing for use in defense and agriculture.

Character recognition is helping to detect fraud and national security assessments.

Advantages of Neural Networks

Fault tolerance

In a neural network, even if a few neurons are not working properly, that would not prevent the neural networks from generating outputs.

Real-time Operations

Neural networks can learn synchronously and easily adapt to their changing environments.

Adaptive Learning

Neural networks can learn how to work on different tasks. Based on the data given to produce the right output.

Parallel processing capacity

Neural networks have the strength and ability to perform multiple jobs simultaneously.

Disadvantages of Neural Networks

Unexplained behavior of the network

Neural networks provide a solution to a problem. Due to the complexity of the networks, it doesn’t provide the reasoning behind “why and how” it made the decisions it made. Therefore, trust in the network may be reduced.

Determination of appropriate network structure

There is no specified rule (or rule of thumb) for a neural network procedure. A proper network structure is achieved by trying the best network, in a trial and error approach. It is a process that involves refinement.

Hardware dependence

The pieces of equipment of a neural network are dependent on one another. By which we mean, that neural networks require (or are highly dependent on) processors with adequate processing capacity.

Conclusion

The neural network field is rapidly expanding. It is critical to learn and grasp the concepts in this sector in order to work with them. This article has discussed the many types of neural networks. By investigating this discipline, you may utilize neural networks to tackle data challenges in other domains.

Top comments (2)

Collapse
 
felix715 profile image
felix715

The neural network field is rapidly expanding. It is critical to learn and grasp the concepts in this sector in order to work with them. This article has discussed the many types of neural networks. By investigating this discipline, you may utilize neural networks to tackle data challenges in other domains. Best wishes!

Collapse
 
musingila profile image
jeremiah wycliffe

nice work