1 views collected around this technical thread.
This article introduces the fundamentals of multi‑objective optimization, explains the NSGA‑II algorithm’s non‑dominated sorting, crowding distance, and selection mechanisms, and demonstrates its application to a production‑line case study with a complete Python implementation and visualized Pareto front.
This article introduces the Differential Evolution (DE) algorithm, detailing its core concepts of mutation, crossover, and selection, outlines the step-by-step procedure, provides a Python implementation, compares DE with Genetic Algorithms, and highlights practical applications across engineering, machine learning, and image processing.
Particle Swarm Optimization (PSO), inspired by bird flocking behavior, is a simple yet powerful evolutionary computation technique that updates particle positions and velocities using personal and global bests, offering fast convergence, parallelism, and wide applications across function optimization, neural networks, pattern recognition, and robotics.
Particle Swarm Optimization (PSO), inspired by bird flocking behavior, is a simple yet powerful population‑based metaheuristic that updates particle velocities and positions using individual and global bests, offering fast convergence, robustness, and wide applications across function optimization, neural networks, classification, and robotics.
This article surveys neural architecture search, classifying existing methods, describing common search spaces—including global and cell‑based designs—detailing optimization strategies such as reinforcement learning, evolutionary algorithms, surrogate models, one‑shot and differentiable approaches, and highlighting recent results and trends in the field.