# Nature Inspired Optimization Algorithms — Introduction

“Look deep into the Nature and then you will understand everything better”

- Albert Einstein

For those who take time to observe and contemplate mother nature, it would be one of the most valuable treasure trove of ideas where inspirations could be drawn. Nature comes with amazing solutions for things which humans take granted as we have seen it for so long.

Be it the shape of a king fisher who sweeps through the air, a massive whale which swims through the deep blue ocean, a bird which glides in the high sky effortlessly have their own characteristics which makes those acts seamless. From the early days, humans have begun to observe these and have drawn many inspirations from mother nature to invent and improve the everyday needs. For examples, inventions of airplanes, bullet trains, parachutes, submarines and even the simple tools like blades, injection needles are Biomimicry with the nature’s creative solutions.

Experts in the data science field are also of no difference in this aspect and have immensely relied on biological instances for inspiration. Below are few of such instances where natures solutions are taken as the answers to the complex optimization problems.

## Optimization

Optimization is a mathematical study, which searches for the best suited solution among a sea of possible alternatives. Be it engineering, medicine, economics or any other field the need of optimization is a commonly across all the domains. Maximising the profit or revenue, minimising the cost or resources, scheduling the work to get the optimal production are few examples which will be seen as some applications of utmost importance in the current business world.

The underlining methodology of mathematical optimization is to define an objective function which needed to be maximised or minimised depending on the problem at hand and take combinations of multiple parameters as input. Then a search will be performed to find out the combination of parameters providing the best value.

For an example, in the below figure if the surface of the graph represents the possible solutions, what the optimization algorithm should do is to take the current solution to the global optimum location.

According to the problem types, the algorithms usually try to intelligently drive the solution to the global optimums efficiently and without being trapped in local optimum locations.

The simplest method to perform an optimization is through ** Brute Force Algorithm**. What this algorithm do is trying all possibilities and selecting the best solution without any technique to improve the search methodology. When the possible alternatives keep increasing, the practicality of this reduce vastly.

To tackle this, over the years, multiple algorithms have been built. Whilst the simple problems could be solved from more traditional optimization algorithms with the aid of assumptions or modifications, when the problems get more complicated like when the issues are multimodal or having many local optimums, more traditional algorithms were found to be inflexible. This is when the mother nature has come to the aid with its sophisticated solutions to derive better solutions for the real world problems. Further, these nature inspired algorithms properly balance the process of ** exploration** which is a deviation from normal space, seeking for new, unknown regions and enhancing the solution space and

**where potential solution is searched by exploiting the information from existing solutions in the search space leading to an optimum solution. Generally, too much exploitation would end up stuck in a local optimum and too much exploration might end up not being able to find the optimum solution.**

*exploitation*Accordingly, to the ** no free lunch theorem** by David Wolpart(1996) there is no one universal solution or algorithm which works better than any other on machine learning tasks, the nature inspired algorithms also do not answer all the questions similarly for all the applications. However, scientists and researchers are coming up with many deviations of the natural phenomena and improving them in multiple ways to adopt them to different kind of problems faced, so that way to reach the optimum solution will be more intelligent and efficient.

Therefore, many variants of one algorithm exist in the field and in the next series of posts I will explain multiple nature inspired algorithms.