Wolf Condition

Protected: Conjugate gradient and nonlinear conjugate gradient methods as continuous optimization in machine learning

Conjugate gradient methods as continuous machine learning optimization for digital transformation, artificial intelligence, and machine learning tasks (moment method, nonlinear conjugate gradient method, search direction, inertia term, Polak-Ribiere method, linear search, Wolf condition, Dai-Yuan method, strong Wolf condition, Fletcher-Reeves method, global convergence, Newton method, rapid descent method, Hesse matrix, convex quadratic function, conjugate gradient method, minimum eigenvalue, maximum eigenvalue, affine subspace, conjugate direction method, coordinate descent method)

2023.02.07

アルゴリズム:Algorithms幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Gauss-Newton and natural gradient methods as continuous optimization for machine learning

Gauss-Newton and natural gradient methods as continuous machine learning optimization for digital transformation, artificial intelligence, and machine learning tasks Sherman-Morrison formula, one rank update, Fisher information matrix, regularity condition, estimation error, online learning, natural gradient method, Newton method, search direction, steepest descent method, statistical asymptotic theory, parameter space, geometric structure, Hesse matrix, positive definiteness, Hellinger distance, Schwarz inequality, Euclidean distance, statistics, Levenberg-Merkert method, Gauss-Newton method, Wolf condition

2023.01.24

アルゴリズム:Algorithms幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Basics of gradient method (linear search method, coordinate descent method, steepest descent method and error back propagation method)

Fundamentals of gradient methods utilized in digital transformation, artificial intelligence, and machine learning tasks (linear search, coordinate descent, steepest descent and error back propagation, stochastic optimization, multilayer perceptron, adaboost, boosting, Wolf condition, Zotendijk condition, Armijo condition, backtracking methods, Goldstein condition, strong Wolf condition)

2022.12.20

アルゴリズム:Algorithms微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra集合論:Set theory