Neural Network & It's use-cases

Objectives:-

In this article , we see the power of neural network. Also learn how neural network works and much more about it...

Neural Network:-

• Neural networks are a set of algorithms, they are designed to mimic the human brain, that is designed to recognize patterns. They interpret data through a form of machine perception by labeling or clustering raw input data.
• The concept of the artificial neural network was inspired by human biology and the way neurons of the human brain function together to understand inputs from human senses.

Why we need Neural Network ?

• Let’s take a moment to consider the human brain. Human brain contain billions of neurons that are connected to each other. The brain has a very complex structure. It’s capable of quickly assessing and understanding the context of numerous different situations. 
• Computers are very fast . But computers struggle to react to situations in a similar way. They can't take decisions like human beings.
• On the other hand , Human brain is so intelligent . But humans are weak/slow in calculation part. That's why we gives intelligence to the computer .This is called Artificial Intelligence. We provides this intelligence by the help of the neural network algorithm.
• So computer can recognize the pattern inside the data and take the decisions.

Artificial Neural Networks Architecture

The functioning of the Artificial Neural Networks is similar to the way neurons work in our nervous system. The Neural Networks go back to the early 1970s when Warren S McCulloch and Walter Pitts coined this term. In order to understand the workings of ANNs, let us first understand how it is structured. In a neural network, there are three essential layers –

1. Input Layers
2. Hidden Layers
3. Output Layer

1. Input Layers :- The input layer is the first layer of an ANN that receives the input information in the form of various texts, numbers, audio files, image pixels, etc.

2. Hidden Layers:- In the middle of the ANN model are the hidden layers. There can be a single hidden layer, as in the case of a perceptron or multiple hidden layers. These hidden layers perform various types of mathematical computation on the input data and recognize the patterns that are part of.

We can use multiple Hidden layer to get more neurons according to the data.

3. Output Layer:- In the output layer, we obtain the result that we obtain through rigorous computations performed by the middle layer.

Types of Neural Networks

There are different kinds of deep neural networks — and each has advantages and disadvantages, depending upon the use. Examples include:

1. Convolutional Neural Networks

Convolutional neural networks (CNNs) contain five types of layers:-

1. input
2. convolution
3. pooling
4. fully connected
5. output.

Each layer has a specific purpose, like summarizing, connecting or activating. Convolutional neural networks have popularized image classification and object detection. However, CNNs have also been applied to other areas, such as natural language processing and forecasting.

2. Recurrent Neural Networks

• Recurrent neural networks (RNNs) use sequential information such as time-stamped data from a sensor device or a spoken sentence, composed of a sequence of terms.
• Unlike traditional neural networks, all inputs to a recurrent neural network are not independent of each other, and the output for each element depends on the computations of its preceding elements.
• RNNs are used in fore-casting and time series applications, sentiment analysis and other text applications.

3. Feedforward Neural Networks

Feedforward neural networks, in which each perceptron in one layer is connected to every perceptron from the next layer. Information is fed forward from one layer to the next in the forward direction only. There are no feedback loops.

4. Autoencoder Neural Networks

Autoencoder neural networks are used to create abstractions called encoders, created from a given set of inputs. Although similar to more traditional neural networks, autoencoders seek to model the inputs themselves, and therefore the method is considered unsupervised.

The premise of autoencoders is to desensitize the irrelevant and sensitize the relevant. As layers are added, further abstractions are formulated at higher layers (layers closest to the point at which a decoder layer is introduced). These abstractions can then be used by linear or nonlinear classifiers.

Use Cases of Neural Network

1. Face Recognition using Neural Networks:-

Face recognition entails comparing an image with a database of saved faces to identify the person in that input picture. The face detection mechanism involves dividing images into two parts; one containing targets (faces) and one providing the background.

The associated assignment of face detection has direct relevance to the fact that images need to be analyzed and faces identified, earlier than they can be recognized.

2. Neural networks in medicine

Neural Networks (ANN) are currently a ‘hot’ research area in medicine and it is believed that they will receive an extensive application to biomedical systems in the next few years. At the moment, the research is mostly on modelling parts of the human body and recognizing diseases from various scans (e.g. cardiograms, CAT scans, ultrasonic scans, etc.).

• Neural networks are ideal in recognizing diseases using scans since there is no need to provide a specific algorithm on how to identify the disease.
• Neural networks learn by example so the details of how to recognize the disease are not needed. What is needed is a set of examples that are representative of all the variations of the disease. The quantity of examples is not as important as the ‘quantity’. The examples need to be selected very carefully if the system is to perform reliably and efficiently.

3. Neural Networks in Optimizing Store Layout

Artificial Neural Networks can also improve physical store layouts. Their ability to quickly analyze and monitor stock levels allows companies to see which products are selling well and which aren’t.

Poorly performing products can then be placed on offer or moved to a more eye-catching position in the store. These systems also allow companies to see which products are frequently purchased together. Placing commonly purchased products close together encourages people buying one item to purchase the other.

You can then surround these products with other possible purchases. Not only does this cut the waste of perishable products but it can also help to prevent a backlog building in the warehouse. Fashion giants H&M are looking to these applications to transform their business model.

4. Improving Search Engine Functionality

During the 2015 Google I/O keynote address in San Francisco, Google revealed they were working on improving their search engine. These improvements are powered by a 30 layer deep Artificial Neural Network. This depth of layers, Google believes, allows the search engine to process complicated searches such as shapes and colours.

Using an Artificial Neural Network allows the system to constantly learn and improve. This allows Google to constantly improve its search engine. Within a few months, Google was already noticing improvements in search results.

• The company reported that its error rate had dropped from 23% down to just 8%. Google’s application shows that neural networks can help to improve search engine functionality.
• Similar Artificial Neural Networks can be applied to the search feature on many e-commerce websites. This means that many companies can improve their website search engine functionality.
• Amazon has reported sales increases of 29% following improvements to its recommendation systems. This allows customers with only a vague idea of what they want to easily find the perfect item.

5. Dealing with Malware

Traditional malware solutions such as regular firewalls detect malware by using a signature-based detection system. A database of known threats is run by the company which updates it frequently to incorporate new threats that were introduced recently. While this technique is efficient against these threats, it struggles to deal with more advanced threats.

Deep learning algorithms are capable of detecting more advanced threats and are not reliant on remembering known signatures and common attack patterns. Instead, they learn the system and can recognize suspicious activities that might indicate the presence of bad actors or malware.

6. Spam and Social Engineering Detection

Natural Language Processing (NLP), a deep learning technique, can help you to easily detect and deal with spam and other forms of social engineering. NLP learns normal forms of communication and language patterns and uses various statistical models to detect and block spam.

7.. Network Traffic Analysis

Deep learning ANNs are showing promising results in analyzing HTTPS network traffic to look for malicious activities. This is very useful to deal with many cyber threats such as SQL injections and DOS attacks.

8. User Behavior Analytics

Tracking and analyzing user activities and behaviors is an important security practice for any organization. It is much more challenging than recognizing traditional malicious activities against the networks since it bypasses security measures and often doesn’t raise any flags and alerts.

For example, when insider threats occur and employees use their legitimate access in malicious intent, they are not infiltrating the system from the outside, which renders many cyber defense tools useless against such attacks.

User and Entity Behavior Analytics (UEBA) is a great tool against such attacks. After a learning period, it can pick up normal employee behavioral patterns and recognize suspicious activities, such as accessing the system in unusual hours, that possibly indicate an insider attack and raise alerts.

Some other applications of Neural network

1. Aerospace: Aircraft component fault detectors and simulations, aircraft control systems, high-performance auto-piloting, and flight path simulations
2. Automotive: Improved guidance systems, development of power trains, virtual sensors, and warranty activity analyzers
3. Electronics: Chip failure analysis, circuit chip layouts, machine vision, non-linear modeling, prediction of the code sequence, process control, and voice synthesis
4. Manufacturing: Chemical product design analysis, dynamic modeling of chemical process systems, process control, process and machine diagnosis, product design and analysis, paper quality prediction, project bidding, planning and management, quality analysis of computer chips, visual quality inspection systems, and welding quality analysis
5. Robotics: Forklift robots, manipulator controllers, trajectory control, and vision systems
6. Telecommunications: ATM network control, automated information services, customer payment processing systems, data compression, equalizers, fault management, handwriting recognition, network design, management, routing and control, network monitoring, real-time translation of spoken language, and pattern recognition (faces, objects, fingerprints, semantic parsing, spell check, signal processing, and speech recognition)

Conclusion

we can say that the most promising feature of the Artificial Neural Network is its ability to learn. The learning process of brain alters its neural structure. The increasing or decreasing the strength of its synaptic connections depending on their activity.

Thanks,