Clonal Selection Algorithm
The clonal selection algorithm is inspired by the way biological immune systems respond to antigens.
When your immune system detects an invader, it selects immune cells with the highest affinity, clones them, and introduces mutations to create diversity. This process, called affinity maturation, enables adaptation and memory.
The clonal selection algorithm uses these ideas for optimization:
- Evaluate candidate solutions for their affinity (solution quality);
- Clone those with higher affinity more often;
- Mutate clones to generate new variations.
This process explores the solution space and focuses on promising areas.
123456789101112131415161718192021222324252627282930313233import numpy as np # Objective function: maximize f(x) = -x**2 + 5 def affinity(x): return -x**2 + 5 # Initial candidate solutions population = np.random.uniform(-5, 5, size=10) # --- Main Clonal Selection Loop --- for generation in range(5): # Evaluate affinities affinities = np.array([affinity(ind) for ind in population]) # Select top candidates num_selected = 4 selected_indices = affinities.argsort()[-num_selected:] selected = population[selected_indices] # Clone proportionally to affinity num_clones = [int(5 * (affinity(ind) - min(affinities)) / (max(affinities) - min(affinities) + 1e-6)) + 1 for ind in selected] clones = np.concatenate([[ind] * n for ind, n in zip(selected, num_clones)]) # Mutation: add small noise mutation_strength = 0.1 mutated_clones = clones + np.random.normal(0, mutation_strength, size=clones.shape) # Form new population population = np.concatenate([selected, mutated_clones]) # Keep population size fixed population = np.random.choice(population, size=10, replace=False) print("Best solution:", population[np.argmax([affinity(ind) for ind in population])])
Diversity and Adaptation in Clonal Selection
The clonal selection algorithm maintains diversity by mutating clones, generating new candidate solutions and avoiding premature convergence. Through repeated selection, cloning, and mutation—known as affinity maturation—the population adapts over time. This process balances exploitation of high-quality solutions with exploration of new possibilities, making the algorithm effective for complex optimization tasks.
Grazie per i tuoi commenti!
Chieda ad AI
Chieda ad AI
Chieda pure quello che desidera o provi una delle domande suggerite per iniziare la nostra conversazione
Awesome!
Completion rate improved to 6.25Clonal Selection Algorithm
Scorri per mostrare il menu
The clonal selection algorithm is inspired by the way biological immune systems respond to antigens.
When your immune system detects an invader, it selects immune cells with the highest affinity, clones them, and introduces mutations to create diversity. This process, called affinity maturation, enables adaptation and memory.
The clonal selection algorithm uses these ideas for optimization:
- Evaluate candidate solutions for their affinity (solution quality);
- Clone those with higher affinity more often;
- Mutate clones to generate new variations.
This process explores the solution space and focuses on promising areas.
123456789101112131415161718192021222324252627282930313233import numpy as np # Objective function: maximize f(x) = -x**2 + 5 def affinity(x): return -x**2 + 5 # Initial candidate solutions population = np.random.uniform(-5, 5, size=10) # --- Main Clonal Selection Loop --- for generation in range(5): # Evaluate affinities affinities = np.array([affinity(ind) for ind in population]) # Select top candidates num_selected = 4 selected_indices = affinities.argsort()[-num_selected:] selected = population[selected_indices] # Clone proportionally to affinity num_clones = [int(5 * (affinity(ind) - min(affinities)) / (max(affinities) - min(affinities) + 1e-6)) + 1 for ind in selected] clones = np.concatenate([[ind] * n for ind, n in zip(selected, num_clones)]) # Mutation: add small noise mutation_strength = 0.1 mutated_clones = clones + np.random.normal(0, mutation_strength, size=clones.shape) # Form new population population = np.concatenate([selected, mutated_clones]) # Keep population size fixed population = np.random.choice(population, size=10, replace=False) print("Best solution:", population[np.argmax([affinity(ind) for ind in population])])
Diversity and Adaptation in Clonal Selection
The clonal selection algorithm maintains diversity by mutating clones, generating new candidate solutions and avoiding premature convergence. Through repeated selection, cloning, and mutation—known as affinity maturation—the population adapts over time. This process balances exploitation of high-quality solutions with exploration of new possibilities, making the algorithm effective for complex optimization tasks.
Grazie per i tuoi commenti!
