Podcast
Questions and Answers
What is the basis of Genetic Algorithm (GA) searching technique?
What is the basis of Genetic Algorithm (GA) searching technique?
- Deterministic algorithms
- Mechanics of natural selection and genetics (correct)
- First or second derivatives
- Heuristic functions
In Genetic Algorithms (GAs), what is meant by 'survival of the fittest'?
In Genetic Algorithms (GAs), what is meant by 'survival of the fittest'?
- All parents equally produce children
- A random selection of parents produce children
- The parents that are fittest are allowed to produce children (correct)
- The parents that are weakest are allowed to reproduce
What does a Genetic Algorithm (GA) search for in terms of points?
What does a Genetic Algorithm (GA) search for in terms of points?
- The best point available
- Randomly scattered points
- A single point
- A population of points (correct)
Which function does a Genetic Algorithm (GA) use directly to evaluate solutions?
Which function does a Genetic Algorithm (GA) use directly to evaluate solutions?
What type of rules does a Genetic Algorithm (GA) use for decision-making?
What type of rules does a Genetic Algorithm (GA) use for decision-making?
Why does a Genetic Algorithm (GA) work with encoding of parameter sets instead of the parameters themselves?
Why does a Genetic Algorithm (GA) work with encoding of parameter sets instead of the parameters themselves?
What is the purpose of mutation in genetic algorithms?
What is the purpose of mutation in genetic algorithms?
Which type of crossover involves swapping alternating segments of parents' genetic material?
Which type of crossover involves swapping alternating segments of parents' genetic material?
In Uniform Crossover, how are genes treated during the crossover operation?
In Uniform Crossover, how are genes treated during the crossover operation?
What happens in Whole Arithmetic Recombination when the mixing ratio (α) is 0.5?
What happens in Whole Arithmetic Recombination when the mixing ratio (α) is 0.5?
How does One Point Crossover differ from Multi Point Crossover?
How does One Point Crossover differ from Multi Point Crossover?
What is the key difference between Crossover and Mutation in genetic algorithms?
What is the key difference between Crossover and Mutation in genetic algorithms?
What is the main difference between Stochastic Universal Sampling (SUS) and Roulette Wheel Selection?
What is the main difference between Stochastic Universal Sampling (SUS) and Roulette Wheel Selection?
What is a key advantage of Stochastic Universal Sampling over Roulette Wheel Selection?
What is a key advantage of Stochastic Universal Sampling over Roulette Wheel Selection?
When is Rank Selection typically employed in genetic algorithms?
When is Rank Selection typically employed in genetic algorithms?
What distinguishes Stochastic Universal Sampling from Tournament Selection?
What distinguishes Stochastic Universal Sampling from Tournament Selection?
How does Tournament Selection encourage diversity in parent selection?
How does Tournament Selection encourage diversity in parent selection?
What is the purpose of representing probabilities on a roulette wheel in Genetic Algorithms?
What is the purpose of representing probabilities on a roulette wheel in Genetic Algorithms?
Why do fitter individuals have a higher chance of becoming parents in Fitness Proportionate Selection?
Why do fitter individuals have a higher chance of becoming parents in Fitness Proportionate Selection?
Which selection method in Genetic Algorithms relies on dividing a circular wheel into pies proportional to fitness values?
Which selection method in Genetic Algorithms relies on dividing a circular wheel into pies proportional to fitness values?
What happens in Genetic Algorithms when the fitness can take a negative value?
What happens in Genetic Algorithms when the fitness can take a negative value?
How does Roulette Wheel Selection determine the portion of the circle for each individual solution?
How does Roulette Wheel Selection determine the portion of the circle for each individual solution?
What is the main distinction between Stochastic Universal Sampling (SUS) and Roulette Wheel Selection?
What is the main distinction between Stochastic Universal Sampling (SUS) and Roulette Wheel Selection?
What does the GA do in situations where there is a loss in the selection procedure towards fitter individuals?
What does the GA do in situations where there is a loss in the selection procedure towards fitter individuals?
How are parents selected in the GA when the fitness value concept is removed?
How are parents selected in the GA when the fitness value concept is removed?
What does the higher rank of an individual in the GA population indicate?
What does the higher rank of an individual in the GA population indicate?
In the given example, which chromosome has the highest fitness value?
In the given example, which chromosome has the highest fitness value?
What is the probability of selection for Chromosome P6 in the Roulette Wheel Selection?
What is the probability of selection for Chromosome P6 in the Roulette Wheel Selection?
How are mating parents selected after spinning in the Roulette Wheel Selection?
How are mating parents selected after spinning in the Roulette Wheel Selection?
Flashcards are hidden until you start studying
Study Notes
Genetic Algorithm Based Searching
- Genetic Algorithm (GA) is a searching technique based on the mechanics of natural selection and natural genetics.
- GA is based on the "survival of the fittest" theory, where the fittest parents are allowed to produce children (new states).
- GA simulates the process of evolution, considering evolution as an optimization problem where every successor generation is better.
Differences Between GA and Other Searching Methods
- GA works with encoding of parameter sets, not the parameters themselves.
- GA searches for a population of points, not a single point.
- GA uses objective function value (also called fitness function) directly, rather than any heuristic function or first or second derivatives.
- GA uses stochastic rules (based on probability or random numbers) rather than deterministic algorithms.
Genetic Algorithm Phases
- The algorithm begins with an initial population, which is a set of randomly selected states that are satisfactory to the problem.
- The initial population may contain any sequence of states from the start city.
Genetic Algorithm Flow Chart
- GA involves crossover and mutation operations to produce new offspring.
- Crossover is used for exploration, while mutation is used for exploitation.
Crossover Operators
- One-point crossover: a random crossover point is selected, and the tails of the two parents are swapped to get new offspring.
- Multi-point crossover: alternating segments are swapped to get new offspring.
- Uniform crossover: each gene is treated separately, and a coin is flipped to decide whether or not it will be included in the offspring.
- Whole arithmetic recombination: a weighted average of the two parents is taken to produce new offspring.
GA Tuning Parameters
- Population size: 50, 100
- Crossover rate: 0.5 to 0.9
- Mutation rate: 0.01
- Fitness function
Selection Methods in GA
- Roulette Wheel Selection: a probability of selection is calculated for each population, and a fixed point is chosen on the wheel circumference.
- Fitness Proportionate Selection: every individual can become a parent with a probability proportional to its fitness value.
- Stochastic Universal Sampling (SUS): similar to roulette wheel selection, but with multiple fixed points.
- Tournament Selection: K individuals are selected at random, and the best is chosen to become a parent.
- Rank Selection: individuals are ranked according to their fitness, and the selection of parents depends on the rank.
Example of GA
- The initial population and fitness function values are given, and a mating pool is generated using roulette wheel and ranking selection methods.
- Crossover operator is applied using single point crossover.
Studying That Suits You
Use AI to generate personalized quizzes and flashcards to suit your learning preferences.
