グラフ理論

Protected: Calculation of marginal probability distribution – Kikuchi approximation

Application of graphical models to stochastic generative models for digital transformation, artificial intelligence, and machine learning tasks; calculation of marginal probability distributions in the generalized stochastic propagation method with Kikuchi free energy functions and comparison with Bethe free energy functions and Hasse diagrams

2022.07.21

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分:Calculus推論技術:inference Technology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 Bayesian Estimation with Concrete Examples

Calculate the fundamentals of Bayesian estimation (exchangeability, de Finetti's theorem, conjugate prior distribution, posterior distribution, marginal likelihood, etc.) used in probabilistic generative models for digital transformation, artificial intelligence, and machine learning tasks, based on concrete examples (Dirichlet-multinomial distribution model, gamma-gaussian distribution model).

2022.07.20

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分:Calculus推論技術:inference Technology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 Gaussian Processes(4)Hyperparameter Estimation and Generalization of Gaussian Process Regression

Hyperparameter estimation using the gradient descent method of Gaussian process regression for stochastic generative models utilized in digital transformation, artificial intelligence, and machine learning tasks (SCG method, L-BFGS method, global solution using MCMC)

2022.07.19

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分:Calculus推論技術:inference Technology数理論理学:Mathematical logic最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Computing the Peripheral Probability Distribution 2 – Bethe Approximation

Variational methods using the Bethe approximation to compute marginal probability distributions in probability propagation methods for probability estimation using graphical models utilized in digital transformation, artificial intelligence, and machine learning tasks.

2022.07.13

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分: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 Gaussian Processes(3)Gaussian Process Regression Model

Computation and optimization of regression models and predictive distributions using Gaussian processes, which are dimensionless stochastic generative models used in digital transformation, artificial intelligence, and machine learning tasks

2022.07.11

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分:Calculus推論技術:inference Technology数理論理学:Mathematical logic最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Calculation of marginal probability distributions – Probability Propagation Method

Compute the probability distribution around graphical models in probabilistic generative models used in digital transformation, artificial intelligence , and machine learning tasks, such as Bayesian estimation, using probability propagation methods

2022.07.06

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Various probability distributions

Overview of various probabilistic models used as approximate models for probabilistic generative models utilized in digital transformation, artificial intelligence, and machine learning tasks (Student's t distribution, Wishart distribution, Gaussian distribution, gamma distribution, inverse gamma distribution, Dirichlet distribution, beta distribution, categorical distribution, Poisson distribution, Bernoulli distribution)

2022.07.05

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分: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 Gaussian Processes(2)Gaussian Processes and Kernels

Gaussian processes and kernel functions (Mattern kernel, character kernel, Fisher kernel, HMM's marginalized kernel, linear kernel, exponential kernel, periodic kernel, RBF kernel), which are dimensionless stochastic generative models used for digital transformation, artificial intelligence and machine learning tasks

2022.07.04

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分:Calculus推論技術:inference Technology最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra

Protected: Partitioning Methods in Support Vector Machines (2) DCDM Algorithm for Linear SVM

DCDM algorithm (dual coordinate descent method algorithm), an efficient algorithm for processing large amounts of (sparse) data on support vector machines (algorithm for linear SVM used in LIBLINEAR) used in digital transformation (DX), artificial intelligence (AI) and machine learning (ML) tasks.

2022.07.01

アルゴリズム:Algorithmsグラフ理論微分積分:Calculus時系列データ解析最適化:Optimization機械学習:Machine Learning画像認識技術異常検知・変化検知確率・統計:Probability and Statistics自然言語処理:Natural Language Processing

Protected: Graphical model with factor graph representation

An overview of factor graph models, a more generalized version of graphical models used in probabilistic generative models for digital transformation (DX), artificial intelligence (AI), and machine learning (ML) tasks

2022.06.29

アルゴリズム:Algorithmsグラフ理論ベイズ推定微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics線形代数:Linear Algebra