確率・統計:Probability and Statistics

Protected: Sequential Update Type Anomaly Detection by Mixture Distribution Model – Jensen’s Inequality and EM Method

Overview of sequential update anomaly detection using mixture distribution models (Jensen's inequality, EM method), which is the most popular method used for digital transformation and artificial intelligence tasks.

2021.12.09

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

Protected: Anomaly detection using the nearest neighbor method-Dealing with multimodal distributions and the Riemannian metric

Anomaly and change detection by the nearest neighbor method using Riemannian measurement to deal with multimodal data for digital transformation and artificial intelligence tasks.

2021.12.08

推論技術:inference Technology機械学習:Machine Learning異常検知・変化検知確率・統計:Probability and Statistics

Protected: Anomaly detection using simple Bayesian method -Differences from binary classification

Overview of Simple Bayesian Methods for Multivariate Anomaly/Change Detection for Digital Transformation and Artificial Intelligence Tasks

2021.12.07

異常検知・変化検知確率・統計:Probability and Statistics

Protected: Anomaly detection by T2 method for hoteling-Mahalanobis distance and chi-square distribution

Anomaly and change detection using the T2 method (Mahalanobis distance) of hoteling used in digital transformation and artificial intelligence tasks.

2021.12.06

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

Protected: Basic concept of anomaly and change detection – Neyman-Pearson Decision Rule

An Introduction to Machine Learning for Anomaly and Change Detection Used in Digital Transformation and Artificial Intelligence Tasks

2021.12.05

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

Protected: Applications of Markov chain Monte Carlo methods (Ising, combinatorial optimization, particle physics)

Examples of Markov Chain Monte Carlo (MCMC) applications in digital transformation , artificial intelligence, and machine learning tasks, such as Ising, combinatorial optimization (traveling salesman problem), and particle physics, are discussed.

2021.12.04

機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Applications of Markov chain Monte Carlo methods (Bayesian inference)

Overview of the application of MCMC methods to Bayesian inference for digital transformation , artificial intelligence , and machine learning tasks, and description of various algorithms

2021.12.02

C言語機械学習:Machine Learning確率・統計:Probability and Statistics自然言語処理:Natural Language Processing

Protected: MCMC method for calculating stochastic integrals: Algorithms other than Metropolis method (Gibbs sampling, MH method)

An overview of MCMC using Gibbs sampling and MH methods for probability integral computation for digital transformation and artificial intelligence task applications.

2021.11.30

微分積分:Calculus機械学習:Machine Learning確率・統計:Probability and Statistics自然言語処理:Natural Language Processing

Protected: MCMC method for calculating stochastic integrals: Algorithms other than Metropolis method (HMC method)

Algorithm and C implementation of the Hybrid Monte Calro method applied to complex stochastic integral calculations for digital transformation and artificial intelligence tasks.

2021.11.29

C言語深層学習:Deep Learning確率・統計:Probability and Statistics自然言語処理:Natural Language Processing

Machine Learning Professional Series: Topic Models Post-Reading Notes

Topic models using probability generation models to extract sentence topics to be used in digital transformation (DX) and artificial intelligence (AI) tasks.

2021.11.28

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