Category: Bio-​inspired optimization algorithms for machine learning

In 1992, Koza proposed genetic programming. It is an expansion to genetic algorithm. Genetic programming characterizes a tree-​type non-​direct encoding of a probable solution, and computer program might be used in which search is applied directly to the solution. Genetic programming takes up variable-​length representation, whereas fixed-​length encoding is adopted by genetic algorithm. In genetic…

In 1975, Holland proposed a genetic algorithm which is a stochastic algorithm based on evolution for optimization. This algorithm follows the theory of the “survival of the fittest” proposed by Charles Darwin. First, a solution population called chromosomes is initialized. It represents the problem in the bit vector form. Then the fitness of every chromosome is…

Evolutionary computation is a concept in ML whose main objective is to increase the gain knowledge from the phenomena of collectiveness in adaptive population for problem-​solvers utilizing the iterative progress including selection, growth, development, reproduction and survival as in population. EAs are algorithms of optimization which are nondeterministic or cost based. Genetic algorithm, genetic programming,…

There are two branches of optimization of problems known as exact methods and heuristics. BIOAs solve heuristic problems by imitating the strategies of nature. There are two main and booming classes in BIOAs. Those are evolutionary algorithms (EAs) and swarm-​based algorithms (SBAs). EAs are influenced by the evolution in nature, and SBAs are driven by…

ML facilitates systems to recognize patterns from current available algorithms and datasets and develop feasible solution concepts. In ML algorithms, to recognize the patterns it is required to feed the system with the required algorithms and huge data in advance. Then ML carries out some tasks. First it finds, extracts and summarizes the pertinent data.…

ML techniques along with image processing algorithm are used in precision agriculture to increase food production in agricultural fields. Previous data available at different stages of farming are used to predict the conditions to improve production by means of ML algorithms. ML algorithms are useful at different stages of agriculture, such as yield prediction, disease…

With the increase in population, the food production also needs to be increased drastically with the limited available sources. To enhance productivity in farming, so many sophisticated tools are there. Nowadays, internet of things (IoT) and machine learning (ML) are playing a big role in agriculture industry [1, 2].