微分積分:Calculus

Protected: Stochastic coordinate descent as a distributed process for batch stochastic optimization

Stochastic coordinate descent as a distributed process for batch stochastic optimization utilized in digital transformation, artificial intelligence, and machine learning tasks (COCOA, convergence rate, SDCA, γf-smooth, approximate solution of subproblems, stochastic coordinate descent, parallel stochastic coordinate descent, parallel computing process, Communication-Efficient Coordinate Ascent, dual coordinate descent)

2023.02.22

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学: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: Quasi-Newton Method as Sequential Optimization in Machine Learning(1) Algorithm Overview

Quasi-Newton methods as continuous machine learning optimization for digital transformation, artificial intelligence, and machine learning tasks (BFGS formulas, Lagrange multipliers, optimality conditions, convex optimization problems, KL divergence minimization, equality constrained optimization problems, DFG formulas, positive definite matrices, geometric structures, secant conditions, update laws for quasi-Newton methods, Hesse matrices, optimization algorithms, search directions, Newton methods)

2023.02.21

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

Protected: Example of Machine Learning with Bayesian Inference: Variational Inference for Poisson Mixture Models

Examples of machine learning with Bayesian inference utilized for digital transformation, artificial intelligence, and machine learning tasks: variational inference for Poisson mixed models (Gibbs sampling, variational inference, algorithm, ELBO, computation, variational inference algorithm, latent variable parameters, posterior distribution, Dirichlet distribution, gamma distribution)

2023.02.20

アルゴリズム:Algorithmsグラフ理論ベイズ推定幾何学: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: Application of Neural Networks to Reinforcement Learning Policy Gradient, which implements a strategy with a function with parameters.

Application of Neural Networks to Reinforcement Learning for Digital Transformation, Artificial Intelligence, and Machine Learning tasks Policy Gradient to implement strategies with parameterized functions (discounted present value, strategy update, tensorflow, and Keras, CartPole, ACER, Actor Critoc with Experience Replay, Off-Policy Actor Critic, behavior policy, Deterministic Policy Gradient, DPG, DDPG, and Experience Replay, Bellman Equation, policy gradient method, action history)

2023.02.16

アルゴリズム:Algorithmsグラフ理論スパースモデリングマルチエージェントシステム幾何学:Geometry強化学習微分積分: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: Network analysis with Pagerank using Clojure Glittering

Network analysis with Pagerank (label propagation, Twitter user group analysis, influencers, communities, community graphs, accounts, followers, dumping factor, page rank algorithm) using Clojure Glittering for digital transformation, artificial intelligence and machine learning tasks.

2023.02.15

Clojureアルゴリズム:Algorithmsグラフ理論微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra関係データ学習集合論:Set theory

Protected: Exp3.P measures and lower bounds for the adversarial multi-armed bandit problem Theoretical overview

Theoretical overview of Exp3.P measures and lower bounds for adversarial multi-arm bandit problems utilized in digital transformation, artificial intelligence, and machine learning tasks cumulative reward, Poly INF measures, algorithms, Arbel-Ruffini theorem, pseudo-riglet upper bounds for Poly INF measures, closed-form expressions, continuous differentiable functions, Audibert, Bubeck, INF measures, pseudo-riglet upper bounds for INF measures, random choice algorithms, optimal order measures, highly probable riglet upper bounds) closed form, continuous differentiable functions, Audibert, Bubeck, INF measures, pseudo-riglet lower bounds, random choice algorithms, measures of optimal order, highly probable riglet upper bounds

2023.02.10

アルゴリズム:Algorithmsオンライン学習スパースモデリングバンディッド問題幾何学:Geometry強化学習微分積分: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: Overview of C-Support Vector Machines by Statistical Mathematics Theory

Support vector machines based on statistical mathematics theory used in digital transformation, artificial intelligence, and machine learning tasks C-support vector machines (support vector ratio, Markov's inequality, probability inequality, prediction discriminant error, one-out-of-two cross checking method, LOOCV, the discriminant, complementarity condition, main problem, dual problem, optimal solution, first order convex optimization problem, discriminant boundary, discriminant function, Lagrangian function, limit condition, Slater constraint assumption, minimax theorem, Gram matrix, hinge loss, margin loss, convex function, Bayes error, regularization parameter)

2023.02.09

アルゴリズム:Algorithmsスパースモデリング幾何学: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: Distributed processing of on-line stochastic optimization

Distributed online stochastic optimization for digital transformation, artificial intelligence, and machine learning tasks (expected error, step size, epoch, strongly convex expected error, SGD, Lipschitz continuous, gamma-smooth, alpha-strongly convex, Hogwild!), parallelization, label propagation method, propagation on graphs, sparse feature vectors, asynchronous distributed SGD, mini-batch methods, stochastic optimization methods, variance of gradients, unbiased estimators, SVRG, mini-batch parallelization of gradient methods, Nesterov's acceleration method, parallelized SGD)

2023.02.08

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学: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集合論:Set theory

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: Theory of Noisy L1-Norm Minimization as Machine Learning Based on Sparsity (2)

Theory of noisy L1 norm minimization as machine learning based on sparsity for digital transformation, artificial intelligence, and machine learning tasks numerical examples, heat maps, artificial data, restricted strongly convex, restricted isometric, k-sparse vector, norm independence, subdifferentiation, convex function, regression coefficient vector, orthogonal complementary space

2023.02.06

アルゴリズム:Algorithmsスパースモデリング幾何学: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