幾何学:Geometry

Protected: Applying Neural Networks to Reinforcement Learning Deep Q-Network Applying Deep Learning to Value Assessment

Application of Neural Networks to Reinforcement Learning for Digital Transformation, Artificial Intelligence, and Machine Learning tasks Deep Q-Network Prioritized Replay, Multi-step applying deep learning to value assessment Deep Q-Network applying deep learning to value assessment (Prioritized Replay, Multi-step Learning, Distibutional RL, Noisy Nets, Double DQN, Dueling Network, Rainbow, GPU, Epsilon-Greedy method, Optimizer, Reward Clipping, Fixed Target Q-Network, Experience Replay, Average Experience Replay, Mean Square Error, Mean Squared Error, TD Error, PyGame Learning Enviroment, PLE, OpenAI Gym, CNN

2023.02.02

pythonアルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学:Geometry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線形代数:Linear Algebra集合論:Set theory

Protected: An example of machine learning by Bayesian inference: inference by Gibbs sampling of a Poisson mixture model

Examples of machine learning with Bayesian inference utilized for digital transformation, artificial intelligence, and machine learning tasks: inference by Gibbs sampling of Poisson mixed models (algorithm, sampling of unobserved variables, Dirichlet distribution, gamma distribution, conditional distribution, categorical distribution, posterior distribution, simultaneous distribution, superparameter, knowledge model, latent variable) categorical distribution, posterior distribution, simultaneous distribution, hyperparameters, knowledge models, data generating processes, latent variables)

2023.01.30

アルゴリズム:Algorithmsグラフ理論ベイズ推定幾何学: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

Protected: Representation Theorems and Rademacher Complexity as the Basis for Kernel Methods in Statistical Mathematics Theory

Representation theorems and Rademacher complexity as a basis for kernel methods in statistical mathematics theory used in digital transformation, artificial intelligence, and machine learning tasks Gram matrices, hypothesis sets, discriminant bounds, overfitting, margin loss, discriminant functions, predictive semidefiniteness, universal kernels, the reproducing kernel Hilbert space, prediction discriminant error, L1 norm, Gaussian kernel, exponential kernel, binomial kernel, compact sets, empirical Rademacher complexity, Rademacher complexity, representation theorem

2023.01.26

アルゴリズム:Algorithmsグラフ理論幾何学:Geometry微分積分:Calculus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: Batch Stochastic Optimization – Stochastic Variance-Reduced Gradient Descent and Stochastic Mean Gradient Methods

Batch stochastic optimization for digital transformation, artificial intelligence, and machine learning tasks - stochastic variance reduced gradient descent and stochastic mean gradient methods (SAGA, SAG, convergence rate, regularization term, strongly convex condition, improved stochastic mean gradient method, unbiased estimator, SVRG, algorithm, regularization, step size, memory efficiency, Nekaterov's acceleration method, mini-batch method, SDCA)

2023.01.25

アルゴリズム:Algorithms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集合論:Set theory

Protected: Gauss-Newton and natural gradient methods as continuous optimization for machine learning

Gauss-Newton and natural gradient methods as continuous machine learning optimization for digital transformation, artificial intelligence, and machine learning tasks Sherman-Morrison formula, one rank update, Fisher information matrix, regularity condition, estimation error, online learning, natural gradient method, Newton method, search direction, steepest descent method, statistical asymptotic theory, parameter space, geometric structure, Hesse matrix, positive definiteness, Hellinger distance, Schwarz inequality, Euclidean distance, statistics, Levenberg-Merkert method, Gauss-Newton method, Wolf condition

2023.01.24

アルゴリズム:Algorithms幾何学:Geometry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線形代数:Linear Algebra

Protected: Application of Neural Networks to Reinforcement Learning Value Function Approximation, which implements value evaluation as a function with parameters.

Application of Neural Networks to Reinforcement Learning used for Digital Transformation, Artificial Intelligence, and Machine Learning tasks Examples of implementing value evaluation with functions with parameters (CartPole, Q-table, TD error, parameter update, Q-Learning, MLPRegressor, Python)

2023.01.19

アルゴリズム:Algorithmsグラフ理論幾何学:Geometry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線形代数:Linear Algebra

Protected: Batch Stochastic Optimization – Stochastic Dual Coordinate Descent

Stochastic dual coordinate descent algorithms as batch-type stochastic optimization utilized in digital transformation, artificial intelligence, and machine learning tasks Nesterov's measurable method, SDCA, mini-batch, computation time, batch proximity gradient method, optimal solution, operator norm, maximum eigenvalue , Fenchel's dual theorem, principal problem, dual problem, proximity mapping, smoothing hinge loss, on-line type stochastic optimization, elastic net regularization, ridge regularization, logistic loss, block coordinate descent method, batch type stochastic optimization

2023.01.11

アルゴリズム:Algorithmsスパースモデリング幾何学: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

Overview of meta-heuristics and reference books

Overviews Meta-heuristics can be algorithms used to solve optimization problems. An optimization problem is on...

2023.01.08

アルゴリズム:Algorithms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集合論:Set theory

Protected: Big Data and Bayesian Learning – The Importance of Small Data Learning

Big Data and Bayesian Learning for Digital Transformation (DX), Artificial Intelligence (AI), and Machine Learning (ML) Tasks - Importance of Small Data Learning

2023.01.07

アルゴリズム:Algorithmsグラフ理論ベイズ推定幾何学:Geometry微分積分:Calculus最適化:Optimization機械学習:Machine Learning確率・統計:Probability and Statistics

Geometric approach to data

Geometric approaches to data utilized in digital transformation, artificial intelligence, and machine learning tasks (physics, quantum information, online prediction, Bregman divergence, Fisher information matrix, Bethe free energy function, the Gaussian graphical models, semi-positive definite programming problems, positive definite symmetric matrices, probability distributions, dual problems, topological, soft geometry, topology, quantum information geometry, Wasserstein geometry, Lupiner geometry, statistical geometry)

2022.12.25

アルゴリズム:Algorithmsグラフ理論スパースモデリング幾何学: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