Artificial Neural Network and Evolutionary Computation – AI vs Humans

This is the third post of the series in AI vs Humans. This post will take a Look into the algorithm of ANN and Evolutionary Computation. If you have missed the first two posts, I would suggest you to read it.

Lets straight away start with the algorithms, be patient as it might be a little geeky. However, I won’t be including any mathematical explanation. It will simple, plain English with examples.

Artificial Neural Network

Artificial Neural Network (ANN) is set of Artificial Neurons, which are connected together and interact as a group. The interaction is based on several mathematical and complex algorithms. This is an extension to Neural Network, which is biological meaning it relates to humans animals or any carbon based organic creature.

Neural Network models in Artificial Intelligence are ANN. ANN implies more on maths which in turn is used for information processing, which depends on how the Neurons are connected and what environmental factors make them respond.

The above Figure explains how ANN works. The artificial neurons are connected to each other like human neurons. In fact, the inspiration of making ANN was from biology. Every neuron had the capability to call certain functions or forward the request to underlying neurons with the information sent from the previous neuron. This makes the work of ANN simple. Looking into the figure we can see, how each neuron(a circle in the figure imitates one neuron) contacts the other which in turn to others.

Input is given to neurons which in turn call others for underlying hidden functions and outputs the result.

Due to availability of millions of neurons and high connectivity it is also possible for neurons to connect or call the required function through some other way. This is called as routing. Like in case you are traveling on the road and there is a huge traffic ahead, you de tour to another way, similarly neurons choose to change the behavior and give the same result even if there is high information processing. It might become a little slow as its not optimal path.

Evolutionary Computation

Evolutionary Computation Algorithms involve things related to evolution of AI, which is similar to humans algorithms, are being written to make AI to be more human. It includes reproduction, recombination, mutation,survival of the fittest etc.

It might be not possible for a robot or an AI program to give birth biologically but they can always make another, but the real question is how will they evolve like humans evolve with time. For example, a  program can build another program, depending on his ability to program, his efficiency to produce another code, “Program Creating Another Program”.

They will be surviving on the basis of their efficiency and computational speed. We can imagine a program changing it own code to work better or even produce another program as a child of it.

Learning can be another basis of their evolution. In Ai based Games, they change the strategy as the user changes his way of playing. They take into consideration of previous data and the algorithm to predict what’s the next move. Thus, making the program smarter as it meets more new conditions.

It is predicted that after AI and Robot reach a stable state, they will have an equivalent place like a human does. We will have small programs or even a humanoid having similar rights as we do.

The next post will be the last post of this series; I will cover the Current and Future state of AI including some good live examples and link.


About Ashish Mohta

A Professional Tech blogger, Editor and Writer who talks about solving day to day problems of people who use computer. His expertise are in Windows 7, Microsoft Office, Software, Mobile Apps and Video Posts.

Leave a Reply