Neural Networks and its Industry Use cases at Starbucks and Google

What are Neural networks?

Neural networks are a set of algorithms inspired by the functioning of the human brain. Generally when you open your eyes, what you see is called data and is processed by the Neurons(data processing cells) in your brain, and recognizes what is around you. That’s how similar Neural Networks work. They take a large set of data, process the data(draws out the patterns from data), and outputs what it is.

The observation of nature has triggered many important innovations. One with profound socio-economic consequences arose in the attempt to mimic the human brain. Although far from understanding its inner workings, a structure of interconnected specialized cells exchanging electrochemical signals was observed. Some imitation attempts were made until finally, Frank Rosenblatt came out with an improved mathematical model of such cells, the Perceptron (1958).

The Perceptron

Today’s Perceptron, at times generalized as the ‘neuron’, ‘node’ or ‘unit’ in the context of Artificial Neural Networks, can be visually described as below:

perceptron

It operates in the following manner: every input variable is multiplied by its weight, and all of them, together with another special input named ‘bias’, are added together. This result is passed to the ‘activation function’, which finally provides the numerical output response (‘neuron activation’). The weights are a measure of how much an input affects the neuron, and they represent the main ‘knobs’ we have at our disposal to tune the behavior of the neuron. The Perceptron is the basic building block of Artificial Neural Networks.

Deep Neural Networks (DNN)

Deep Neural Networks are the combination of inputs and outputs of multiple different Perceptrons on a grand scale, where there may be a large number of inputs, outputs, and neurons, with some variations in the topology, like the addition of loops, and optimization techniques around it, as you can see in the picture below:

MUTI-LAYER

We can have as many inputs, outputs, and layers in between as needed. These kinds of networks are called feedforward networks, due to the direction of data flowing from input to output.

• The leftmost layer of input values in the picture (in blue) is called the ‘input layer’ (with up to millions of inputs).
• The rightmost layer of output perceptrons (in yellow) is called the ‘output layer’ (there can be thousands of outputs). The green cells represent the output value.
• The layers of perceptrons in between (in red) are called ‘hidden layers’ (there can be up to hundreds of hidden layers, with thousands of neurons).

The word ‘deep’ refers to this layered structure. Although there is not total agreement on the naming, in general, we can start to talk about Deep Neural Networks, once there are more than 2 hidden layers.

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.

These include analyzing data, transcribing speech into text, powering facial recognition software, or predicting the weather.

There are many types of Artificial Neural networks. Each has its own specific use case. 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 feed-forward neural network. This is a basic system where information can travel in only one direction, from input to output.

The most commonly used type of Artificial Neural Network is the recurrent neural network. In this system, data can flow in multiple directions. As a result, these networks have greater learning ability. Consequently, they are used to carry out complex tasks such as language recognition.

Other types of Artificial Neural Networks include convolutional neural networks, Hopfield networks, and Boltzmann machine networks.

Starbucks: Targeted Marketing Campaigns

Through unsupervised learning, Artificial Neural Networks are able to identify customers with similar characteristics.

This allows businesses to group together customers with similarities, such as economic status or preferring vinyl records to downloaded music. Supervised learning systems allow Artificial Neural Networks to set out a clear aim for your marketing strategy. Like unsupervised systems, they can also segment customers into similar groupings.

However supervised learning systems are also able to match customer groupings to the products they are most likely to buy. This application of technology can increase profits by driving sales.

Starbucks has used Artificial Neural Networks and targeted marketing to keep customers engaged with their app. The company has integrated its rewards system location and purchase history on its app.

This allows them to offer an incredibly personalized experience, helping to increase revenue by $2.56 billion.

Google: Improving Search Engine Functionality

During the 2015 Google I/O Keynote 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 colors.

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.

That’s all for today! I’ll be back with some new articles very soon, thanks! 🤗

Muhammad Tabish Khanday

LinkedIn: https://www.linkedin.com/in/mtabishk/