WHAT is AI ?

Data Analytics, Artificial Intelligence, Machine Learning, Deep Learning, – Where to use and Why?

Data Analytics, Machine Learning, Deep Learning, and Artificial Intelligence are the current buzzwords in the corporate world.

The concepts were there long before, but the recent hype is due to the massive amounts of data that is getting generated daily and the enormous computational power that modern day computers hold.

ORIGIN

The field of AI research was born at a workshop at Dartmouth College in 1956, where the term « Artificial Intelligence » was coined by John McCarthy to distinguish the field from cybernetics and escape the influence of the cyberneticist Norbert Wiener.

Attendees Allen Newell (Carnegie Mellon University), Herbert Simon (CMU), John McCarthy (MIT), Marvin Minsky (MIT) and Arthur Samuel (IBM) became the founders and leaders of AI research.

In the 1980s and 1990s, researchers Geoffrey Hinton, Yann LeCun and Yoshua Bengio laid the groundwork for what would revolutionize artificial intelligence, with the « Artificial Neural Networks » (ANN), Deep Learning is inspired by the workings of the human brain

Artificial Intelligence

Artificial Intelligence is the field of computer science that is associated with the concept of machines “thinking like humans” to perform tasks such as learning, problem-solving, planning, reasoning and identifying patterns.

Is Machine Learning the same as AI?

When people refer to “artificial intelligence,” they often really mean machine learning. Machine learning is a subset of AI.

Machine learning (ML) involves creating algorithms that can recognize patterns in large, evolving data sets, and drawing conclusions from past experience by using that data.

ML is often used to predict future outcomes based on historical data.

For example, organizations use machine learning to predict how many of their products will be sold in future fiscal quarters based on a particular demographic; or estimate which customer profile has the highest probability to become dissatisfied or the most loyal to your brand. Such predictions allow better business decisions, more personal user experience, and the potential to reduce customer retention costs.

DEEP LEARNING

Deep Learning is the sub-field of Machine Learning which works on the principle of Neural Networks. Now, the structure of the neural nets is akin to our brain where the data is based through several layers of nets to make accurate predictions.

From Biological NEURON to a Mathematical Model

Based on ANN, Deep Learning allows the computer to learn how to see, interact, predict and create on its own – skills that were thought to be reserved for the human intellect.

Neural networks and deep learning are two of the most important concepts in the domain of Machine Learning.

All these individual nodes are neurons, they have the same structures and are working as explained above. Neurons are categorized into different layers:

  • Input layers feed the input,
  • neurons in the hidden layers do the processing, and
  • the output layer gives output.

ARTIFICIAL NEURON

There is an important object in any neural network called “Neuron”. Every neuron has inputs (x) which are the processed outputs of the preceding neurons.

McCullow et Pitts (1943)
  • Every neuron has inputs (x) which are the processed outputs of the preceding neurons.
  • Weight (w) is then associated with each input (x), their products are then added together to form an expression similar to the one given below:

x1*w1 + x2*w2+ x3*w3 + … + xn*wn

  • A BIASb‘ is added to the above expression and passed through an activation function, the result of which is the value of the given neuron, (b= w0)

Activation Function

Activation functions are used to add non-linearity to neural networks. They squeeze the values into a smaller range. There are different activation functions available that are used in deep learning. For example, a binary step function squashes the value to 0 or 1. It takes the input and if the input is less than 0, the output is 0 and if the input is equal or greater than zero, the output is 1.

The working of each neuron in a complex neural network remains the same. However, different neurons may have different activation functions. Example of Activation Functions :


WEB Search

Recent Post

EDGE AI Summit

Welcome to our website !

Archived Blog