機械学習:Machine Learning

Basic Similarity(5) Data Expansion Techniques

Natural Language Similarity for Digital Transformation (DX), Artificial Intelligence (ML), Machine Learning (ML). Similarity for ontology matching using an extended data approach.

2021.07.13

セマンテックウェブ技術:Semantic web Technology推論技術:inference Technology検索技術:Search Technology機械学習:Machine Learning深層学習:Deep Learning自然言語処理:Natural Language Processing

Basic Similarity (4) Internal structure-based approach

Similarity estimation of natural language for digital transformation (DX), artificial intelligence (AI), and machine learning (ML) applications based on data types and domain elements.

2021.07.12

推論技術:inference Technology検索技術:Search Technology機械学習:Machine Learning深層学習:Deep Learning自然言語処理:Natural Language Processing

Basic Similarity(3) A language-based approach

Linguistic approaches to natural language similarity assessment that can be used for digital transformation (DX), artificial intelligence (AI), and machine learning (ML), including multilingual support.

2021.07.09

推論技術:inference Technology検索技術:Search Technology機械学習:Machine Learning自然言語処理:Natural Language Processing

Basic Similarity (2) String-based approach

Summary of various methods for structuring raw text as a basis for natural language processing for digital transformation (DX), artificial intelligence (AI), and machine learning (ML) applications, normalization techniques, substring handling, edit distance, token-based Distance and path comparison

2021.07.08

推論技術:inference Technology検索技術:Search Technology機械学習:Machine Learning深層学習:Deep Learning自然言語処理:Natural Language Processing

Basic Similarity (1) Overview

Definition and overview of natural language similarity, which is important when applying digital transformation (DX), artificial intelligence (AI), and machine learning (ML), based on ontology matching

2021.07.07

セマンテックウェブ技術:Semantic web Technology推論技術:inference Technology検索技術:Search Technology機械学習:Machine Learning自然言語処理:Natural Language Processing

Explainable Machine Learning

In the first half of Molnar's paper on Explainable Artificial Intelligence, he outlines that explanations can be intrinsic or post-hoc, and in the latter approach, an algorithm is used to construct an explanation from input-output pairs. A good explanation is one that can be compared with counterexamples.

2021.06.25

アルゴリズム:Algorithms機械学習:Machine Learning

one hot vector and category vector with Clojure

Implementation of one-hot-vector and category-vector in Clojure for machine learning applications in natural language processing

2021.06.15

Clojure機械学習:Machine Learning自然言語処理:Natural Language Processing

Protected: Matrix Decomposition -Extraction of relational features between two objects

Extraction of relationships by machine learning, matrix factorization approach, non-negative matrix factorization

2021.05.30

機械学習:Machine Learning線形代数:Linear Algebra

Protected: Clustering Techniques for Asymmetric Relational Data – Probabilistic Block Model and Infinite Relational Model

Machine Learning Extraction of Relationships, Probabilistic Block Model and Infinite Relation Model

2021.05.29

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

Protected: Clustering of symmetric relational data – Spectral clustering

Extraction of relationships, knowledge extraction and prediction, spectral clustering by machine learning for graph analysis, etc.

2021.05.28

最適化:Optimization検索技術:Search Technology機械学習:Machine Learning線形代数:Linear Algebra