Industry usecases of Neural Networks

What is neural network??

NEURAL NETWORKS also known as ARTIFICIAL NEURAL NETWORKS (ARR)is a series of algorithms that endeavors to recognize underlying relationships in a set of data through a process that mimics the way the human brain operates. In this sense, neural networks refer to systems of neurons, either organic or artificial in nature. Neural networks can adapt to changing input; so the network generates the best possible result without needing to redesign the output criteria. The concept of neural networks, which has its roots in artificial intelligence, is swiftly gaining popularity in the development of trading systems.

Types of Neural Networks

? Artificial Neural Networks

? Radial Basis Function Neural Network

? Multilayer Perceptron

? Convolutional Neural Network

? Recurrent Neural Network

? Modular Neural Network

? Sequence-To-Sequence Models

Components of Neural Network

Input Layers, Neurons, and Weights –

In the picture given above, the outermost yellow layer is the input layer. A neuron is the basic unit of a neural network. They receive input from an external source or other nodes. Each node is connected with another node from the next layer, and each such connection has a particular weight. Weights are assigned to a neuron based on its relative importance against other inputs.

When all the node values from the yellow layer are multiplied (along with their weight) and summarized, it generates a value for the first hidden layer. Based on the summarized value, the blue layer has a predefined “activation” function that determines whether or not this node will be “activated” and how “active” it will be.

Let’s understand this using a simple everyday task – making tea. In the tea making process, the ingredients used to make tea (water, tea leaves, milk, sugar, and spices) are the “neurons” since they make up the starting points of the process. The amount of each ingredient represents the “weight.” Once you put in the tea leaves in the water and add the sugar, spices, and milk in the pan, all the ingredients will mix and transform into another state. This transformation process represents the “activation function.”

Neural Network: Architecture

Neural Networks are complex structures made of artificial neurons that can take in multiple inputs to produce a single output. This is the primary job of a Neural Network – to transform input into a meaningful output. Usually, a Neural Network consists of an input and output layer with one or multiple hidden layers within.

In a Neural Network, all the neurons influence each other, and hence, they are all connected. The network can acknowledge and observe every aspect of the dataset at hand and how the different parts of data may or may not relate to each other. This is how Neural Networks are capable of finding extremely complex patterns in vast volumes of data. 

Flow of information In a Neural Network

? Feedforward Networks: In this model, the signals only travel in one direction, towards the output layer. Feedforward Networks have an input layer and a single output layer with zero or multiple hidden layers. They are widely used in pattern recognition.

? Feedback Networks: In this model, the recurrent or interactive networks use their internal state (memory) to process the sequence of inputs. In them, signals can travel in both directions through the loops (hidden layer/s) in the network. They are typically used in time-series and sequential tasks. 

What are Artificial Neural Networks Used for?

Artificial Neural Networks can be used in a number of ways. They can classify information, cluster data, or predict outcomes. ANN’s can be used for a range of tasks. These include analyzing data, transcribing speech into text, powering facial recognition software, or predicting the weather. There are many types of Artificial Neural Network. Each has its own specific use. Depending on the task it is required to process the ANN can be simple or very complex. The most basic type of Artificial Neural Network is a feedforward neural network. This is a basic system where information can travel in only one direction, from input to output.

How do Artificial Neural Networks Work?

As we have seen Artificial Neural Networks are made up of a number of different layers. Each layer houses artificial neurons called units. These artificial neurons allow the layers to process, categorize, and sort information. Alongside the layers are processing nodes. Each node has its own specific piece of knowledge. This knowledge includes the rules that the system was originally programmed with. It also includes any rules the system has learned for itself. This makeup allows the network to learn and react to both structured and unstructured information and data sets. Almost all artificial neural networks are fully connected throughout these layers. Each connection is weighted. The heavier the weight, or the higher the number, the greater the influence that the unit has on another unit. The first layer is the input layer. This takes on the information in various forms. This information then progresses through the hidden layers where it is analysed and processed. By processing data in this way, the network learns more and more about the information. Eventually, the data reaches the end of the network, the output layer. Here the network works out how to respond to the input data. This response is based on the information it has learned throughout the process. Here the processing nodes allow the information to be presented in a useful way.

Neural Network: Algorithms

In a Neural Network, the learning (or training) process is initiated by dividing the data into three different sets:

? Training dataset – This dataset allows the Neural Network to understand the weights between nodes.

? Validation dataset – This dataset is used for fine-tuning the performance of the Neural Network.

? Test dataset – This dataset is used to determine the accuracy and margin of error of the Neural Network.

Once the data is segmented into these three parts, Neural Network algorithms are applied to them for training the Neural Network. The procedure used for facilitating the training process in a Neural Network is known as the optimization, and the algorithm used is called the optimizer. There are different types of optimization algorithms, each with their unique characteristics and aspects such as memory requirements, numerical precision, and processing speed.

Educating Artificial Neural Networks

For artificial neural networks to learn they require a mass of information. This information is known as a training set. If you wanted to teach your ANN to learn how to recognise a cat your training set would consist of thousands of images of a cat. These images would all be tagged “cat”. Once this information has been inputted and analysed the network is considered trained. From now on it will try to classify any future data based on what it thinks it is seeing. So if you present it with a new image of a cat, it will identify the creature. As a check, during the training period, the system’s output is matched against the description of the data it’s analysing. If the information is the same, the learning process is validated. If the information is different backpropagation is used to adjust the learning process. Backpropagation involves working back through the layers, adjusting the set mathematical equations and parameters. These adjustments are made until the output data presents the desired result. This process, deep learning, is what makes the network adaptive. The network is able to learn and adapt as more information is processed.

How Do You Train a Neural Network?

Once you’ve structured a network for a particular application, training (i.e., learning), begins. There are two approaches to training. 

Supervised learning provides the network with desired outputs through manual grading of network performance or by delivering desired outputs and inputs. 

Unsupervised learning occurs when the network makes sense of inputs without outside assistance or instruction.

Tasks Neural Networks Perform

Neural networks are highly valuable because they can carry out tasks to make sense of data while retaining all their other attributes. Here are the critical tasks that neural networks perform:

? Classification: NNs organize patterns or datasets into predefined classes.

? Prediction: They produce the expected output from given input.

? Clustering: They identify a unique feature of the data and classify it without any knowledge of prior data.

? Associating: You can train neural networks to “remember” patterns. When you show an unfamiliar version of a pattern, the network associates it with the most comparable version in its memory and reverts to the latter.

Real-World and Industry Applications of Neural Networks

Here’s a list of neural networks engineering applications currently in use in various industries:

? Aerospace: Aircraft component fault detectors and simulations, aircraft control systems, high-performance auto-piloting, and flight path simulations

? Automotive: Improved guidance systems, development of power trains, virtual sensors, and warranty activity analyzers

? Electronics: Chip failure analysis, circuit chip layouts, machine vision, non-linear modeling, prediction of the code sequence, process control, and voice synthesis

? 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

? Mechanics: Condition monitoring, systems modeling, and control

? Robotics: Forklift robots, manipulator controllers, trajectory control, and vision systems

? 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)

Artificial Neural Networks are Improving Marketing Strategies

By adopting Artificial Neural Networks businesses are able to optimise their marketing strategy. Systems powered by Artificial Neural Networks all capable of processing masses of information. This includes customers personal details, shopping patterns as well as any other information relevant to your business. Once processed this information can be sorted and presented in a useful and accessible way. This is generally known as market segmentation. To put it another way segmentation of customers allows businesses to target their marketing strategies. Businesses can identify and target customers most likely to purchase a specific service or produce. This focusing of marketing campaigns means that time and expense isn’t wasted advertising to customers who are unlikely to engage. This application of Artificial Neural Networks can save businesses both time and money. It can also help to increase profits. The flexibility of Artificial Neural Networks means that their marketing applications can be implemented by most businesses. Artificial Neural Networks can segment customers on multiple characteristics. These characteristics can be as diverse as location, age, economic status, purchasing patterns and anything else relevant to your business.

Applications of neural networks in the pharmaceutical industry

Artificial Neural Networks are being used by the pharmaceutical industry in a number of ways. The most obvious application is in the field of disease identification and diagnosis. It was reported in 2015 that in America 800 possible cancer treatments were in the trial. With so much data being produced, Artificial Neural Networks are being used to help scientists efficiently analyse and interpret it.

ANNs may be able to improve medical diagnoses. Figuring out what is wrong with a patient and then prescribing an effective treatment for them is a complicated process, to say the least. As of today, numerous scientific papers have been published that claim ANNs can both streamline and speed-up diagnoses. At this point, most sources seem to agree that this is simply due to the recorded accuracy of ANNs related to diagnosing certain diseases. One scientific article claims that neural networks can diagnose five specific diseases, including chickenpox with between 90 and 97% accuracy. Another study found that when this sort of diagnostic ability is combined with that of a doctor, the number should rise to an almost perfect level(99.5% accuracy). With this in mind, before we have AI doctors, we’ll likely have AI assistants that augment just about every aspect of a doctor’s job.

A case study of using artificial neural networks for classifying cause of death from verbal autopsy

Abstract

Background 

Artificial neural networks (ANN) are gaining prominence as a method of classification in a wide range of disciplines. In this study ANN is applied to data from a verbal autopsy study as a means of classifying cause of death.

Methods 

A simulated ANN was trained on a subset of verbal autopsy data, and the performance was tested on the remaining data. The performance of the ANN models were compared to two other classification methods (physician review and logistic regression) which have been tested on the same verbal autopsy data.

Results 

Artificial neural network models were as accurate as or better than the other techniques in estimating the cause-specific mortality fraction (CSMF). They estimated the CSMF within 10% of true value in 8 out of 16 causes of death. Their sensitivity and specificity compared favourably with that of data-derived algorithms based on logistic regression models.

Conclusions 

Cross-validation is crucial in preventing the over-fitting of the ANN models to the training data. Artificial neural network models are a potentially useful technique for classifying causes of death from verbal autopsies. Large training data sets are needed to improve the performance of data-derived algorithms, in particular ANN models.

KEY MESSAGES

? Artifical neural networks have potential for classifying causes of death from verbal autopsies.

? Large datasets are needed to train neural networks and for validating their performance.

? Generalizability of neural network models to various settings needs further evaluation.

From Mayuk Das