Regularization

Protected: Batch Stochastic Optimization – Stochastic Variance-Reduced Gradient Descent and Stochastic Mean Gradient Methods

Batch stochastic optimization for digital transformation, artificial intelligence, and machine learning tasks - stochastic variance reduced gradient descent and stochastic mean gradient methods (SAGA, SAG, convergence rate, regularization term, strongly convex condition, improved stochastic mean gradient method, unbiased estimator, SVRG, algorithm, regularization, step size, memory efficiency, Nekaterov's acceleration method, mini-batch method, SDCA)

2023.01.25

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集合論:Set theory

Protected: Basic Framework of Statistical Mathematics Theory

Basic framework of statistical mathematics theory used in digital transformation, artificial intelligence, and machine learning tasks regularization, approximation and estimation errors, Höfding's inequality, prediction discriminant error, statistical consistency, learning algorithms, performance evaluation, ROC curves, AUC, Bayes rules, Bayes error, prediction loss, empirical loss

2022.11.09

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

Protected: Supervised learning and regularization

Overview of supervised learning regression, discriminant and regularization ridge function, L1 regularization, bridge regularization, elastic net regularization, SCAD, group regularization, generalized concatenated regularization, trace norm regularization as the basis of machine learning optimization methods used for digital transformation, artificial intelligence and machine learning tasks

2022.11.08

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

Protected: Structural regularization learning with submodular optimization (1) Regularization and p-norm review

Review of sparse modeling, regularization and p-norm to consider structural regularization learning with submodular optimization, an optimization technique for discrete information for digital transformation, artificial intelligence and machine learning tasks

2022.05.06

IOT技術:IOT TechnologyStream Data Processingアルゴリズム:Algorithmsグラフ理論データベース技術:DataBase Technologyユーザーインターフェース/データビジュアライゼーション微分積分:Calculus数理論理学:Mathematical logic時系列データ解析最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Fundamentals of Submodular Optimization (2) Basic Properties of Submodular Functions

Three basic properties of submodular functions (normalized, non-negative, symmetric) as a basis for optimization algorithms (submodular optimization) of discrete information for digital transformation, artificial intelligence and machine learning tasks and their application to graph cut maximization and minimization problems

2022.04.14

Symbolic Logicグラフ理論推論技術:inference Technology数理論理学最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics関係データ学習

Protected: Reinforcement Learning with Function Approximation (2) – Function Approximation of Value Functions (For Online Learning)

Theory of function approximation online methods gradient TD learning, least-squares based least-squares TD learning (LSTD), GTD2)for reinforcement learning with a huge number of states used in digital transformation , artificial intelligence , and machine learning tasks, and regularization with LASSO.

2022.01.28

オンライン学習強化学習微分積分:Calculus最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning確率・統計:Probability and Statistics

Machine Learning Professional Series Sparsity-Based Machine Learning Reading Notes

Overview of sparse modeling used for regularization and other applications in machine learning for digital transformation , artificial intelligence , and machine learning tasks.

2022.01.15

最適化:Optimization機械学習:Machine Learning深層学習:Deep Learning

Protected: Anomaly detection using sparse structure learning- Graph models and regularization that link broken dependencies between variables to anomalies.

Graph models and regularization that link broken dependencies between variables to anomalies.

2021.12.15

微分積分:Calculus推論技術:inference Technology最適化:Optimization機械学習:Machine Learning異常検知・変化検知確率・統計:Probability and Statistics

This is a good introduction to deep learning (Machine Learning Startup Series)Reading Notes

Overview of deep learning for digital transformation and artificial intelligence tasks, including machine learning, gradient descent, regularization, error back propagation, self-encoders, convolutional neural networks, recurrent neural networks, Boltzmann machines, and reinforcement learning.

2021.11.15

微分積分:Calculus数理論理学:Mathematical logic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