The picture shows on the left side the host, which serves asgenetic database for the horizontal gene transfer, carried out by plasmid vector agents. One weight plasmid on the left side below transports a sequence of weights to the endosymbiont,as well as a structural plasmid above the host transfers theweights, biases and activation functions. On the right side a jump and swap transposon vector mutates the chromosome of the endosymbiont.
Host genetic material
The host within SHOCID consists "rough" solutions to the problem statement, meaning several populations eachconsisting of thousands individuals each of them subject of continuous evolution. Therefore, the host is not only oneorganism, but thousands of organisms in different populations.
The endosymiont within SHOCID is a simulated annealingANN solution, which simulates the cooling of metal.Simulated annealing belongs to the group of metaheuristicalgorithms, suitable for solving optimization or search problems. In physics, the term 'annealing' refers to the veryslow cooling of gas or metal into a crystalline solid of minimum energy configuration . The atoms of suchmaterials have very high energy values at very hightemperatures, which gives the atoms a great deal of freedomin their ability to restructure themselves . The energyvalues of such materials decreases during cooling down. If the ideal speed (continuous temperature reduction) has beenfound, the material will be stable in its structure and moreconsistent then if cooling it down too quick. Simulatedannealing (SA)  algorithms therefore simulate this behaviour, which can also be applied within ANN training.The simulated annealing algorithm always works with twosolutions, the first being the best one having been achieveduntil the point in time , represented by , and thesecond being the one currently being created and comparedwith the first one, represented by(2)If the second one performs better than the first one, thus theoutcome of the above equation is positive, it is used to replacethe latter as the current best one. In some cases, simulatedannealing also makes use of a probability of when to replacea solution with a better one, meaning that in someimplementations a better new solution might not alwaysreplace the actual one:(3), where
represents the current temperature, meaning thevalue that influences the change of weights within a weightmatrix of an ANN:(4)The ratio for changing the weights within anANN is calculated by multiplying the temperature by arandom number . The higher the temperature is, the higher isthe probability of a high weight change. Changes with aspecific temperature are carried out as long as a predefinednumber of iterations (cycles) has not been reached. After having fulfilled the last iteration of a temperature, thealgorithm verifies if the lowest, predefined temperature has been reached. If not, the temperature will be lowered byeither a constant or by logarithmically decreasing it by a ratio between a beginning and an ending temperature, as thefollowing equation shows :(1)The variable s represents the starting temperature, e theending temperature. c represents the cycle count. The aboveequation calculates a ratio that should be multiplied by thecurrent temperature T, which produces a change that willcause the temperature to reach the ending temperature in thespecified number of cycles.The transgenetic vectors are being applied during thesimulated cooling process. Each iteration creates a new possible solution, and each new solution must endure theattacks of both plasmid and transposon vector agents to see if a better solution can be found.II.
The algorithm for applying transgenetic NeuroEvolution isas follows:
Creation of initial host populations.
Randomization of weights and threshold values of each chromosome.
Calculate the network output for the value2.
Evaluate the fitness of each chromosome:a.
Calculate the error for each outputneuron