Neural Network

what is Neural Network??

Neural networks are the workhorses of deep learning. And while they may look like black boxes, deep down they are trying to accomplish the same thing as any other model — to make good predictions.

Let’s start with a really high level overview so we know what we are working with. Neural networks are multi-layer networks of neurons (green nodes) that we use to classify things, make predictions, etc. Below is the diagram of a simple neural network with 2 inputs, 1outputs, and 1hidden layers of neurons.

Neural Network with 1 hidden Layer

Starting from the left, we have:

1. Input of model in orange.
2. Our first hidden layer(there can be more than 1 hidden layer) of neurons in green.
3. The output layer (prediction) of our model in blue.

The connection of dots shows how all the neurons are interconnected and how data travels from the input layer all the way through to the output layer.

Feed Propagation and Back propagation

Remember that forward propagation is the process of moving forward through the neural network (from inputs to the ultimate output or prediction)After the weight is updated we give the updated weight to the neural. Our goal in using a neural net is to arrive at the point of least error as fast as possible

Forward propagation in Neural Network

Back propagation is the reverse. Except instead of signal, we are moving error backwards through our model i.e. input layer.

Backward propagation in Neural Network

Attributes of Neural Networks

With the human-like ability to problem-solve — and apply that skill to huge datasets — neural networks possess the following powerful attributes:

• Adaptive Learning: Like humans, neural networks model non-linear and complex relationships and build on previous knowledge. For example, software uses adaptive learning to teach math and language arts.
• Self-Organization: The ability to cluster and classify vast amounts of data makes neural networks uniquely suited for organizing the complicated visual problems posed by medical image analysis.
• Real-Time Operation: Neural networks can (sometimes) provide real-time answers, as is the case with self-driving cars and drone navigation.
• Prognosis: NN’s ability to predict based on models has a wide range of applications, including for weather and traffic.
• Fault Tolerance: When significant parts of a network are lost or missing, neural networks can fill in the blanks. This ability is especially useful in space exploration, where the failure of electronic devices is always a possibility.

Use-case of IDM’s Watson

IBM is one of the largest and oldest of the legacy technology companies, but IBM has managed to transition from older business models to newer revenue streams remarkably well. None of IBM’s products demonstrate this better than its renowned AI, Watson.

• Identify meaningful relationships in raw data and has the potential to be applied in almost every field of medicine, including drug development, treatment decisions, patient care, and financial and operational decisions.
• Can extract relevant information from large amounts of data and generate actionable insights that could be applied to many applications.
• the feature of Neural network that analyze and extract different features different layers. This process allows the system to identify new data or images.

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.

There are many more use-case other than this too like Automation of Cyberattack Countermeasures and many more