機械学習:Machine Learning

Iwanami Data Science Series vol.3 “Causal Theory Reading Causality from Real World Data” Reading Memo

Summary Techniques to examine "causal relationships" that are not "correlations" are "causal inference" and "cau...

2022.02.27

推論技術:inference Technology機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Fundamentals of statistical causal inference (1) – Definition of causality by counterfactual model and structural equation model

Foundations of Statistical Causal Inference for Digital Transformation , Artificial Intelligence and Machine Learning Tasks: Defining Causality in Counterfactual Models and Structural Equation Models

2022.02.25

推論技術:inference Technology機械学習:Machine Learning確率・統計:Probability and Statistics

Protected: Algorithms for Network Flow Problems

The solution of the maximum communication volume problem by Ford-Fulkerson's algorithm and its relation to the minimum cut problem, the maximum matching problem for nipartite graphs which is a special case of the maximum flow problem, the general matching problem and the minimum cost flow problem are described.

2022.02.24

アルゴリズム:Algorithmsグラフ理論最適化:Optimization機械学習:Machine Learning

Zen and Buddha Bot as Told by Artificial No-Brains

The early history of the dialogue engine, starting with the importance of dialogue and Eliza to the meaning of words, philosophy by Wittgenstein, meta-literature by James Joyce, Zen thought (the Ten Oxen) for enlightenment, Zen questions and answers and Buddhabot.

2022.02.19

Symbolic Logicweb技術:web technologyセマンテックウェブ技術:Semantic web Technologyチャットボットデータベース技術:DataBase Technology仏教:Buddhism機械学習:Machine Learning禅:Zen自然言語処理:Natural Language Processing

Protected: Combinatorial online prediction

Combinatorial, online prediction problems with a set of discrete structures as the decision space for digital transformation , artificial intelligence , and machine learning task utilization.

2022.02.15

オンライン学習幾何学: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

Protected: Online prediction based on randomness

Randomness-based FPL(Follow the Perturbed Leader) Strategy and Gumbel Distribution for Improving Online Predictive Performance for Digital Transformation , Artificial Intelligence and Machine Learning Tasks

2022.02.14

オンライン学習幾何学: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

Protected: Online convex optimization (3) exp concavity and ONS

Convex optimization for online prediction for digital transformation , artificial intelligence , and machine learning tasks (the case of exp concavity and ONS).

2022.02.10

オンライン学習幾何学: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

Protected: Online Convex Optimization (2) Complementing FTL Strategies with Regularization

Complementing the FTL strategy by introducing regularization techniques (L2 norm) in online prediction for digital transformation , artificial intelligence , and machine learning tasks.

2022.02.09

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確率・統計:Probability and Statistics

Protected: Online Convex Optimization(1) FTL strategy and BTL supplement

Online Convex Optimization and FTL Strategies with Online Prediction for Digital Transformation , Artificial Intelligence , and Machine Learning Tasks with BTL Supplement

2022.02.08

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確率・統計:Probability and Statistics

Protected: New Developments in Reinforcement Learning (2) – Approaches Using Deep Learning

On seven methods for improving deep reinforcement learning used in digital transformation , artificial intelligence , and machine learning tasks (first generation DQN, dual Q learning (dual DQN method), prioritized experience replay, collision Q networks, distributed reinforcement learning (categorical DQN method) noise networks, n-step cutting returns) and alpha zero

2022.02.07

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