Industry use cases of Neural Networks

What is a Neural Networks ?

• Neural networks are a series of algorithms that mimic the operations of a human brain to recognize relationships between vast amounts of data.
• They are used in a variety of applications in financial services, from forecasting and marketing research to fraud detection and risk assessment.

Neural networks, in the world of finance, assist in the development of such process as time-series forecasting, algorithmic trading, securities classification, credit risk modeling and constructing proprietary indicators and price derivatives. A neural network works similarly to the human brain’s neural network. A 'neuron' in a neural network is a mathematical function that collects and classifies information according to a specific architecture. The network bears a strong resemblance to statistical methods such as curve fitting and regression analysis.

A neural network contains layers of interconnected nodes. Each node is a perceptron and is similar to a multiple linear regression. The perceptron feeds the signal produced by a multiple linear regression into an activation function that may be nonlinear.

In a multi-layered perceptron (MLP), perceptron are arranged in interconnected layers. The input layer collects input patterns. The output layer has classifications or output signals to which input patterns may map. For instance, the patterns may comprise a list of quantities for technical indicators about a security, potential outputs could be 'buy', 'hold' or 'sell'.

Hidden layers fine-tune the input weightings until the neural network’s margin of error is minimal. It is hypothesized that hidden layers extrapolate salient features in the input data that have predictive power regarding the outputs. This describes feature extraction, which accomplishes a utility similar to statistical techniques such as principal component analysis. The building blocks of Neural Network are hidden layers and neurons.

Basic terminologies in Neural Networks

Input Layer– First is the input layer. This layer will accept the data and pass it to the rest of the network.

Hidden Layer– The second type of layer is called the hidden layer. Hidden layers are either one or more in number for a neural network. In the above case, the number is 1. Hidden layers are the ones that are actually responsible for the excellent performance and complexity of neural networks. They perform multiple functions at the same time such as data transformation, automatic feature creation, etc.

Output layer– The last type of layer is the output layer. The output layer holds the result or the output of the problem. Raw images get passed to the input layer and we receive output in the output layer.

Bias- It is an additional parameter in the Neural Network which is used to adjust the output along with the weighted sum of the inputs to the neuron. That's why, Bias is a constant which helps the model in a way that it can fit best for the given data.

Weights- Weights are the coefficients of the equation which you are trying to resolve. Negative weights reduce the value of an output. When a neural network is trained on the training set, it is initialized with a set of weights. These weights are then optimized during the training period and the optimum weights are produced.

Actvation function- Activation function is nothing but a mathematical function that takes in an input and produces an output. The function is activated when the computed result reaches the specified threshold.

Applications of Neural Networks

• Aerospace ? Autopilot aircrafts, aircraft fault detection.
• Automotive ? Automobile guidance systems.
• Military ? Weapon orientation and steering, target tracking, object discrimination, facial recognition, signal/image identification.
• Electronics ? Code sequence prediction, IC chip layout, chip failure analysis, machine vision, voice synthesis.
• Financial ? Real estate appraisal, loan advisor, mortgage screening, corporate bond rating, portfolio trading program, corporate financial analysis, currency value prediction, document readers, credit application evaluators.
• Industrial ? Manufacturing process control, product design and analysis, quality inspection systems, welding quality analysis, paper quality prediction, chemical product design analysis, dynamic modeling of chemical process systems, machine maintenance analysis, project bidding, planning, and management.
• Medical ? Cancer cell analysis, EEG and ECG analysis, prosthetic design, transplant time optimizer.
• Speech ? Speech recognition, speech classification, text to speech conversion.
• Telecommunications ? Image and data compression, automated information services, real-time spoken language translation.
• Transportation ? Truck Brake system diagnosis, vehicle scheduling, routing systems.
• Software ? Pattern Recognition in facial recognition, optical character recognition, etc.
• Time Series Prediction ? ANNs are used to make predictions on stocks and natural calamities.
• Signal Processing ? Neural networks can be trained to process an audio signal and filter it appropriately in the hearing aids.
• Control ? ANNs are often used to make steering decisions of physical vehicles.
• Anomaly Detection ? As ANNs are expert at recognizing patterns, they can also be trained to generate an output when something unusual occurs that misfits the pattern.

Some Industry use cases of Neural Network

> Facebook:

Facebook achieved web dominance by riding a business model of understanding users and feeding them tailored content and advertising. And as the social networking company further builds on its strong position, it leans heavily on deep learning models.

- Understanding text with deep learning:

It's not all about images and videos, though. Facebook also uses natural language processing algorithms to interpret textual content and improve the quality of posts shown to users. Facebook uses an NLP system built around neural networks to identify posts that are excessively promotional, spam or clickbait. The deep learning model filters these types of posts out and keeps them from showing in users' news feeds. There's a huge amount of textual content that's being uploaded on Facebook every day, and understanding that is important to improving customer experience. Deep learning models are helping Facebook develop products by enabling developers to understand content at a large scale.

- Deep learning for computer vision:

For example, computer vision neural network deep learning models are used to interpret the content of photos users have posted and decide which to surface in the "on this day" feature. This Facebook feature shows users' posts that they made on the same day in past years.

So the models underlying the feature have to interpret images and develop a semantic understanding of what's happening to ensure it's something people would want to be reminded of. It does this in part by identifying people and objects in images and interpreting the context around them. The models were trained on more than a billion photos that have been uploaded to Facebook over the years, and they have to score in real time millions of new images uploaded each day. Tulloch said this is a huge technical challenge, but one for which the convolutional neural networks his team uses are well-suited.

>Siemens:

A Siamese neural network (sometimes called a twin neural network) is an artificial neural network that uses the same weights while working in tandem on two different input vectors to compute comparable output vectors. Often one of the output vectors is precomputed, thus forming a baseline against which the other output vector is compared. This is similar to comparing fingerprints but can be described more technically as a distance function for locality-sensitive hashing.

It is possible to build an architecture that is functionally similar to a siamese network but implements a slightly different function. This is typically used for comparing similar instances in different type sets.

Uses of similarity measures where a twin network might be used are such things as recognizing handwritten checks, automatic detection of faces in camera images, and matching queries with indexed documents. The perhaps most well-known application of twin networks are face recognition, where known images of people are precomputed and compared to an image from a turnstile or similar. It is not obvious at first, but there are two slightly different problems. One is recognizing a person among a large number of other persons, that is the facial recognition problem. DeepFace is an example of such a system. In its most extreme form this is recognizing a single person at a train station or airport. The other is face verification, that is to verify whether the photo in a pass is the same as the person claiming he or she is the same person. The twin network might be the same, but the implementation can be quite different.

>Google:

Google uses neural networks in many ways and also Google has developed it's own Google neural machine translation. Google Neural Machine Translation (GNMT) is a neural machine translation (NMT) system developed by Google and introduced in November 2016, that uses an artificial neural network to increase fluency and accuracy in Google Translate.

GNMT improves on the quality of translation by applying an example-based (EBMT) machine translation method in which the system "learns from millions of examples". GNMT's proposed architecture of system learning was first tested on over a hundred languages supported by Google Translate. With the large end-to-end framework, the system learns over time to create better, more natural translations GNMT is capable of translating whole sentences at a time, rather than just piece by piece. The GNMT network can undertake interlingual machine translation by encoding the semantics of the sentence, rather than by memorizing phrase-to-phrase translations.

Google Translate's NMT system uses a large artificial neural network capable of deep learning. By using millions of examples, GNMT improves the quality of translation, using broader context to deduce the most relevant translation. The result is then rearranged and adapted to approach grammatically based human language. GNMT's proposed architecture of system learning was first tested on over a hundred languages supported by Google Translate. GNMT did not create its own universal interlingua but rather aimed at finding the commonality between many languages using insights from psychology and linguistics. The new translation engine was first enabled for eight languages: to and from English and French, German, Spanish, Portuguese, Chinese, Japanese, Korean and Turkish in 2016.

Conclusion:

So, Finally in this blog we tried to see different use cases of neural networks and some basic concepts and terminologies related to Neural Networks which is playing an important role for solving the Real Use cases in Industry.

Hope you liked the Article :)

Happy Learning !!