Quick Overview

Neural networks are mathematical models that use learning algorithms inspired by the brain to store information. Since neural networks are used in machines, they are collectively called an ‘artificial neural network.’ Nowadays, the term machine learning is often used in this field and is the scientific discipline that is concerned with the design and development of algorithms that allow computers to learn, based on data, such as from sensor data or databases. A major focus of machine-learning research is to automatically learn to recognize complex patterns and make intelligent decisions based on data. Hence, machine learning is closely related to fields such as statistics, data mining, pattern recognition, and artificial intelligence. Neural networks are a popular framework to perform machine learning, but there are many other machine-learning methods, such as logistic regression, and support vector machines.

Similar to the brain, neural networks are built up of many neurons with many connections between them. Neural networks have been used in many applications to model the unknown relations between various parameters based on large numbers of examples. Examples of successful applications of neural networks are classifications of handwritten digits, speech recognition, and the prediction of stock prices. Moreover, neural networks are more and more used in medical applications. Many different types of neural networks exist. Examples of various types of neural networks are Hopfield network, the multilayer perceptron, the Boltzmann machine, and the Kohonen network. The most commonly used and successful neural network is the multilayer perceptron and will be discussed in detail.

The first step toward artificial neural networks came in 1943, when Warren McCulloch, a neurophysiologist, and a young mathematician, Walter Pitts, wrote a paper on how neurons might work. They modeled a simple neural network with electrical circuits. In the 1950s, Rosenblatt’s work resulted in a two-layer network, the perceptron, which was capable of learning certain classifications by adjusting connection weights but also had some limitations. In the early 1980s, researchers showed renewed interest in neural networks.

Neural Networks

Neural Network defined!

An artificial neural network learning algorithm, or neural network, or just neural net

, is a computational learning system that uses a network of functions to understand and translate a data input of one form into a desired output, usually in another form. The concept of the artificial neural network was inspired by human biology and the way neurons of the human brain function together to understand inputs from human senses. 

Neural networks are just one of many tools and approaches used in machine learning algorithms. The neural network itself may be used as a piece in many different machine learning algorithms to process complex data inputs into a space that computers can understand. 

Neural networks are being applied to many real-life problems today, including speech and image recognition, spam email filtering, finance, and medical 

How does it works???

Machine learning algorithms that use neural networks generally do not need to be programmed with specific rules that define what to expect from the input. The neural net learning algorithm instead learns from processing many labeled examples (i.e. data with with “answers”) that are supplied during training and using this answer key to learn what characteristics of the input are needed to construct the correct output. Once a sufficient number of examples have been processed, the neural network can begin to process new, unseen inputs and successfully return accurate results. The more examples and variety of inputs the program sees, the more accurate the results typically become because the program learns with experience.  

This concept can best be understood with an example. Imagine the “simple” problem of trying to determine whether or not an image contains a cat. While this is rather easy for a human to figure out, it is much more difficult to train a computer to identify a cat in an image using classical methods. Considering the diverse possibilities of how a cat may look in a picture, writing code to account for every scenario is almost impossible. But using machine learning, and more specifically neural networks, the program can use a generalized approach to understanding the content in an image. Using several layers of functions to decompose the image into data points and information that a computer can use, the neural network can start to identify trends that exist across the many, many examples that it processes and classify images by their similarities. 

Applications of Neural Network

Neural networks can be applied to a broad range of problems and can assess many different types of input, including images, videos, files, databases, and more. They also do not require explicit programming to interpret the content of those inputs.

Because of the generalized approach to problem solving that neural networks offer, there is virtually no limit to the areas that this technique can be applied. Some common applications of neural networks today, include image/pattern recognition, self driving vehicle trajectory prediction, facial recognition, data mining, email spam filtering, medical diagnosis, and cancer research. There are many more ways that neural nets are used today, and adoption is increasing rapidly.