We have dedicated this post to application of Neural Networks as part of our series of posts on application of Big data and Machine Learning. One way to think of the neural network is to consider the last layer as a logistic regression classifier, and then the hidden layers can be thought of as automatic “feature selectors”. This eliminates the work of manually choosing the correct number of, and power of, the input features. Thus, the NN becomes an automatic power feature selector and can find any linear or non-linear relationship or serve as a classifier of arbitrarily complex sets** (this, assumes only, that there are enough hidden layers and connections to represent the complexity of the model it needs to learn). In the end, a well-functioning NN is expected to learn not just “the relationship” between the input and outputs, but instead we strive for an abstraction or a model that generalizes well.
As a rule of thumb, the neural network cannot learn anything a reasonably intelligent human could not theoretically learn given enough time from the same data, however,
Character Recognition – The idea of character recognition has become very important. Neural networks can be used to recognize handwritten characters.
Image Compression – Neural networks can receive and process vast amounts of information at once, making them useful in image compression. With the Internet explosion and more sites using more images on their sites, using neural networks for image compression is worth a look.
Stock Market Prediction – The day-to-day business of the stock market is extremely complicated due to the influence of a large number of factors. Many factors weigh in like high, low, open and close price, volume, price of other securities etc. as well as economic indicators. Since neural networks can examine a lot of information quickly and sort it all out, they can be used to predict stock prices.
Fraud detection– In recent years, the development of new technologies has also provided further ways in which criminals may commit fraud. Neural networks that can learn suspicious patterns from samples to detect approximate classes, clusters, or patterns of suspicious behavior and use them later to detect frauds.