Artificial Intelligence (AI) and Machine Learning (ML) are two extremely volatile topics in the intel market these days and are used frequently.
Many people believe that they are quite the same things. The two paradigms could be different ways of looking at the same problem However, they are not the same. Therefore, I thought of giving a shot to explain the difference.
In today’s world, with emergence of big data, analytics and other technology changes these two words come up frequently.
In large, Artificial Intelligence is a the broader concept of algorithms which helps machines to perform ‘smart’ tasks. On the other hand, Machine learning is an application of AI that provides data to these algorithms, so they can learn themselves. This data is many of times indicated as training data. As name indicates the data is provided to algorithms purely to train them to better perform the tasks they are doing. Therefore, we can simply say that Machine Learning is simply a way of achieving Artificial Intelligence.
Artificial Intelligence has been around for a long time. However, world simply did not have such amount of training data, which is available today. With influx of web technologies , smart devices, IoT, and other data generating technologies since last decade, the amount of training data available has increased drastically. This gave computer scientists opportunity not only to create self-learning algorithms but also to train them with the data. As compared to early algorithms crated to simply solve complex calculations, today’s AI algorithms are created to mimic how human mind works.
In conclusion we can say that, in ML, the problem is approached bottom-up, where you start with a significant amount of ‘training data’. On the other hand, the earlier AI systems were designed to discover generic patterns and rules without having a lot of training data.
Neural Networks or Artificial neural networks ANN are one of the main tools used in machine learning. They are a system, inspired by human brain, and are intended to replicate the way that we humans learn.
Neural networks consist of input, output layers and in many cases hidden layer consisting of units that transform the input into something that the output layer can use. They are excellent tools for finding patterns which are far too complex or numerous for a human programmer to extract and teach the machine to recognize.
Therefore we can say that, A Neural Network is a system designed to work by analysing information in the same way a human brain does. It can be taught to recognise images, patterns, etc and classify them according to elements they contain.
In the image below you can see that each circular node represents an artificial neuron and an arrow represents a connection from the output of one artificial neuron to the input of another.
In next post we will see..
- What is Deep Learning?
- What is Graphical Models?
- What is Reinforcement Learning?