Neural Network and its Use-Case ✨

The neural network is the base of Deep Learning. It is a subset of Machine Learning where the algorithm is inspired by the human brain. Neural networks take the data as input and train themself to predict the output or produce some other data similar to input data.

Let’s understand how neural network works 🧠

A neural network is consists of neurons which is the core processing unit. Neural networks consist of an input layer, hidden layers, and the output layer.

  • Input Layer: The input layer consists of one or more input variables or feature variables. Which could be denoted as X1, X2, X3,………………….Xn.
  • Hidden Layer: The hidden layer consist of one or more hidden nodes or hidden units. It computes most of the computation tasks required by the neural network.
  • Output Layer: The output layer consists of one or more output units which function is to predict the output.

A neural network can have many hidden layers. More hidden layers increase the accuracy of the model. Each node or neuron in the neural network is composed of two or more functions, a linear function, and an activation function.

The input is fed to the neurons of the first layer. The neurons of the first layer are connected through the neurons of the next layer through channels. Each of these channels is assigned a value called weight. Then the result is calculated with the help of weight and bias and the output is sent to the Activation function. The activation function then decides which neuron of the next layer is to activate or not. In this way, the data is propagated through the network and this is called forward propagation. In the output layer, the neuron with the highest value is propagated and determines the output. Now the predicted output is compared with the actual output and the magnitude of the error determines accuracy in our model. Then this information is given back to the neural network called backward propagation. Based on this information the weights are adjusted and this cycle of forwarding propagation and backward propagation is performed on the multiple inputs. This process continues till our model predicts the correct output in most cases.

✨Industry Use Case of Neural Network

Google — Neural Networks and ‘Machines That Dream’ 👨🏼‍💻

Software engineers at Google have been analyzing the ‘dreams’ of their computers. And it turns out that androids do dream of electric sheep and also pig-snails, camel-birds, and dog-fish. This conclusion has been made after testing the ability of Google’s servers to recognize and create images of common objects — for example, bananas and measuring cups. The result of this experiment is some tessellating Escher-esque artwork with Dali-like quirks.

The Google artificial neural network is like a computer brain, inspired by the central nervous system of animals. When an image is feed into the network, the first layer of ‘neurons’ has a look at it. This layer then ‘talks’ to the next layer, which then has a go at processing the image. This process is repeated 10 to 30 times, with each layer identifying key features and isolating them until it has figured out what the image is. The neural network then tells us what it has valiantly identified the object to be, sometimes with little success. This is the process behind image-recognition.

The Google team then realized that they could reverse the process. They gave the artificial neural network an object and asked it to create an image of that object. The computer then tries to associate it with specific features. When we want a picture of a fork, the computer should figure out that the defining features of a fork are two to four tines and a handle. But things like size, color, and orientation aren’t as important. The images in the picture above were created in order to ascertain whether the computer has understood this sort of distinction.

This technique, which creates images where there aren’t any, is aptly called ‘inceptionism.’ Finally, the designers gave the computer full, free reign over its artwork. The final pieces were beautiful pictures derived from a mechanical mind — what the engineers are calling ‘dreams.’

IBM — Better Healthcare 👨🏼‍⚕️

It is very difficult to create and train a neural network for usage in the healthcare industry because it requires high accuracy. For many years it seemed to be impossible to use this technology for examining patients and diagnosing them. But finally, it has become possible.

IBM Watson is the most powerful artificial intelligence in the world. It took 2 years to train the neural network for medical practice. Millions of pages of medical academic journals, medical records, and other documents were uploaded to the system for its learning. And now it can prompt the diagnosis and propose the best treatment pattern based on the patient’s complaints and anamnesis.

Watson has been deployed in several hospitals and medical centers in recent years, where it demonstrated its aptitude for making highly accurate recommendations in the treatment of certain types of cancers.

Conclusion ✨

As you can see that AI and ML are the future of all industries. These technologies help to make decisions, automate the working processes, prevent fraud and do other important tasks. And they will continue developing.

Thank You!!😊