微分積分:Calculus

Protected: Model-based reinforcement learning(Sparse sampling, UCT, Monte Carlo search tree)

Model-based reinforcement learning (sparse sampling, UCT, Monte Carlo search trees) used for digital transformation artificial intelligence , and machine learning tasks.

2022.01.24

IOT技術:IOT TechnologyStream Data Processing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

Structural Learning

About Structural Learning Learning the structure that data has is important for interpreting what the data is a...

2022.01.22

グラフ理論幾何学: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

Machine Learning Professional Series “Continuous Optimization for Machine Learning” Reading Memo

Summary Continuous optimization in machine learning is a method for solving optimization problems in which varia...

2022.01.22

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: Model-free reinforcement learning (2) – Method iteration (Q-learning, SARSA, Actor-click method)

Value iteration methods Q-learning, SARSA, Actor-critic methods to model-free reinforcement learning for digital transformation , artificial intelligence and machine learning tasks.

2022.01.21

IOT技術:IOT TechnologyStream Data Processing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: Trade-off between exploration and utilization -Regret and stochastic optimal measures, heuristics

Reinforcement learning with regrets, stochastic optimal measures, and heuristics

2022.01.19

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: Planning Problems (2) Implementation of Dynamic Programming (Value Iterative Method and Measure Iterative Method)

Implementation of Dynamic Programming (Value Iteration and Policy Iteration) for Planning Problems as Reinforcement Learning for Digital Transformation , Artificial Intelligence and Machine Learning Tasks

2022.01.18

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: Planning Problems(1) – Approaches Using Dynamic Programming and Theoretical Underpinnings

Reinforcement learning by planning problems (dynamic programming and linear programming) for sequential decision problems in known environments used for digital transformation , artificial intelligence and machine learning tasks.

2022.01.17

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: Evaluating the performance of online learning(Perceptron, Regret Analysis, FTL, RFTL)

Perceptron and Riglet Analysis (FTL, RFTL) for evaluating online learning used for digital transformation , artificial intelligence , and machine learning tasks.

2022.01.14

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: Advanced online learning (4) Application to deep learning (AdaGrad, RMSprop, ADADELTA, vSGD)

Application to online learning in AdaGrad, RMSprop, and vSGD used for digital transformation , artificial intelligence , and machine learning tasks.

2022.01.13

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

Protected: Advanced online learning (3) Application to deep learning (mini-batch stochastic gradient descent, momentum method, accelerated gradient method)

Improving computational efficiency by applying mini-batch stochastic gradient descent, momentum, and accelerated gradient methods to deep learning for digital transformation , artificial intelligence , and machine learning tasks.

2022.01.12

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