Devashish Kumar Pan

Mar 4, 2021

5 min read

Neural Networks

The engine behind Deep Learning.

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.

Neural networks as the name suggests try to mimic neural network existing in the human brain. The brain is a very complex structure, made up of millions of neurons interconnected with each other.

It’s capable of quickly assessing and understanding the context of numerous different situations. Computers struggle to react to situations in a similar way. Artificial Neural Networks are a way of overcoming this limitation.

Artificial Neural Networks can be viewed as weighted directed graphs in which artificial neurons are nodes, and directed edges with weights are connections between neuron outputs and neuron inputs.

The Artificial Neural Network receives information from the external world in the form of pattern and image in vector form. These inputs are mathematically designated by the notation x(n) for n number of inputs.

Each input is multiplied by its corresponding weights. Weights are the information used by the neural network to solve a problem. Typically weight represents the strength of the interconnection between neurons inside the Neural Network.

The weighted inputs are all summed up inside the computing unit (artificial neuron). In case the weighted sum is zero, bias is added to make the output not- zero or to scale up the system response. Bias has the weight and input always equal to ‘1′.

The sum corresponds to any numerical value ranging from 0 to infinity. To limit the response to arrive at the desired value, the threshold value is set up. For this, the sum is passed through an activation function.

The activation function is set to the transfer function used to get the desired output. There are linear as well as the nonlinear activation function.

Some of the commonly used activation function is — binary, sigmoidal (linear) and tan hyperbolic sigmoidal functions(nonlinear).

Neural Networks can be used in a number of ways. They can classify information, cluster data, or predict outcomes. NN’s can be used for a range of tasks. They have many advantages over traditional Machine learning too.

Some of the real life use case of Neural networks include :

Facial Recognition using visual intelligence of machines :- Convolutional Neural Networks allow us to extract a wide range of features from images. Turns out, we can use this idea of feature extraction for face recognition too! This means that the neural network needs to be trained to automatically identify different features of faces and calculate numbers based on that.

By adopting Neural Networks businesses are able to optimize their marketing strategy :- Systems powered by 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. 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.

Fraud Detection & Prevention Services :- Data Mining Tools like Machine Learning, Neural Networks, Cluster Analysis are used to generate Predictive Models to prevent fraud losses. Data Mining is used to quickly detect fraud and search for spot patterns and detect fraudulent transactions. These Models offers real-time fraud analysis to increase profitability.

Developing Targeted Marketing Campaigns :- Through unsupervised learning, Neural Networks are able to identify customers with a similar characteristic. This allows businesses to group together customers with similarities, such as economic status or preferring vinyl records to downloaded music. Supervised learning systems allow Neural Networks to set out a clear aim for your marketing strategy.

Improving Search Engine Functionality :- During 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 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.


Well after reading, browsing and surfing the internet and all the articles that I could find(along with some books here and there), I was able to list a few use cases of Neural Networks.

And at the end I conclude that what I have found doesn’t even scratches the surface of what Neural Networks are capable of. On that matter I am not even sure what neural networks will look like by the time I graduate.

Thank You for reading!!