How Simulated Annealing Finds High‑Quality Solutions: A Step‑by‑Step Guide

This article outlines the step‑by‑step procedure of the Simulated Annealing algorithm, covering initialization, new‑solution generation, incremental objective‑difference calculation, Metropolis acceptance, solution replacement, temperature updating, and includes a concise pseudocode illustration to help practitioners implement the method effectively.

metaheuristicobjective functionoptimization algorithm

0 likes · 4 min read

How Simulated Annealing Finds High‑Quality Solutions: A Step‑by‑Step Guide

Beike Product & Technology

Mar 21, 2019 · Artificial Intelligence

Optimization Foundations and Applications in Machine Learning and Computer Vision

This article introduces how machine learning problems are formulated as optimization tasks, explains the construction of objective functions with examples such as linear regression, robust fitting, regularization, and demonstrates various applications ranging from K‑means clustering to image inpainting and 3D reconstruction.

Computer VisionRegularizationlinear regression

0 likes · 9 min read

Optimization Foundations and Applications in Machine Learning and Computer Vision

Hulu Beijing

Mar 21, 2019 · Artificial Intelligence

How GANs’ Objective Functions Evolved: From JS Divergence to Modern Variants

This article explores the evolution of Generative Adversarial Networks' objective functions, detailing the shift from Jensen‑Shannon divergence to f‑divergence, IPM‑based approaches, and auxiliary losses, while highlighting their impact on stability and performance across image, audio, and text generation tasks.

Deep LearningGANsGenerative Adversarial Networks

0 likes · 9 min read

How GANs’ Objective Functions Evolved: From JS Divergence to Modern Variants