Whenever we come across such articles, we instinctively feel that something doesn't feel right. There are so many posts out there that it is nearly impossible to sort out the right from the wrong. Fake news can be claimed in two ways: First, an argument against the facts. The former can only be accomplished with automated query systems and substantial searches into the internet. The latter is possible through a natural language processing pipeline followed by a machine learning pipeline.

On the Internet, there are a lot of sources that provide enormous amounts of daily news. Further, the demand for information by users has been growing continuously, so it is important to classify the news in a way that lets users access the information they are interested in quickly and efficiently. Using this model, users would be able to identify news topics that go untracked, and/or make recommendations based on their prior interests. Thus, we aim to build models that take news headlines and short descriptions as inputs and produce news categories as outputs. The problem we will tackle is the classification of BBC News articles and their categories.

Every asset has a life cycle and thus requires frequent maintenance. However, we may not want to spend resources too soon as that is a waste and we cannot be too late as it is risky. Thus, "when" to repair is an important problem. Predictive maintenance is a way to predict or forecast the probability of breakdown of a fixed asset. Predictive maintenance is important for all kinds of businesses, from a large company predicting the breakdown of motors to a small businesses predicting the breakdown of printers.

Neural Networks have taken the world of machine learning and predictive modelling in the last 5 years. Neural network have the ability to learn complex relationships in data and have been shown to work for a variety of applications from finance to robotics. Inspired by the human brain, Neural Networks work on the principle of signal transmission from one neuron to the other. Neural networks comprise of mainly three types of node layers -- an input layer, one or more hidden layers, and an output layer. Each node is an artificial neuron which connects to another using a nonlinear function and has an associated weight and threshold.