Deus Ex Machina

Protected: Regret Analysis for Stochastic Banded Problems

Regret analysis for stochastic banded problems utilized in digital transformation, artificial intelligence, and machine learning tasks (sum of equal sequences, gamma function, Thompson extraction, beta distribution, hem probability, Mills ratio, partial integration, posterior sample, conjugate prior distribution, Bernoulli distribution, cumulative distribution function, expected value, DMED measure, UCB measure, Chernoff-Hefding inequality, likelihood, upper bound, lower bound, UCB score, arms)

2023.01.13

アルゴリズム:Algorithms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線形代数:Linear Algebra

Protected: Regenerate nuclear Hilbert spaces as a basis for kernel methods in statistical mathematics theory.

Regenerate kernel Hilbert spaces as a basis for kernel methods in statistical mathematics theory used in digital transformation, artificial intelligence, and machine learning tasks orthonormal basis, Hilbert spaces, Gaussian kernels, continuous functions, kernel functions, complete spaces, inner product spaces, equivalence classes, equivalence relations, Cauchy sequences, linear spaces, norms, complete inner products

2023.01.12

アルゴリズム:Algorithms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: 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

Protected: Newtonian and Modified Newtonian Methods as Sequential Optimization in Machine Learning

Newton and modified Newton methods (Cholesky decomposition, positive definite matrix, Hesse matrix, Newtonian direction, search direction, Taylor expansion) as continuous machine learning optimization for digital transformation, artificial intelligence and machine learning tasks

2023.01.10

アルゴリズム:Algorithms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: What triggers sparsity and for what kinds of problems is sparsity appropriate?

What triggers sparsity and for what kinds of problems is sparsity suitable for sparse learning as it is utilized in digital transformation, artificial intelligence, and machine learning tasks? About alternating direction multiplier method, sparse regularization, main problem, dual problem, dual extended Lagrangian method, DAL method, SPAMS, sparse modeling software, bioinformatics, image denoising, atomic norm, L1 norm, trace norm, number of nonzero elements

2023.01.09

アルゴリズム:Algorithmsスパースモデリングスパースモデリング微分積分: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

Protected: Theory of Noisy L1-Norm Minimization as Machine Learning Based on Sparsity (1)

Theory of L1 norm minimization with noise as sparsity-based machine learning for digital transformation, artificial intelligence, and machine learning tasks Markov's inequality, Heffding's inequality, Berstein's inequality, chi-square distribution, hem probability, union Bound, Boolean inequality, L∞ norm, multidimensional Gaussian spectrum, norm compatibility, normal distribution, sparse vector, dual norm, Cauchy-Schwartz inequality, Helder inequality, regression coefficient vector, threshold, k-sparse, regularization parameter, inferior Gaussian noise

2023.01.06

スパースモデリング機械学習:Machine Learning

Protected: Explainable Artificial Intelligence (10) Model-independent Interpretation (Feature Interaction)

Interaction of features, one of the posterior interpretive models that can be explained and used for digital transformation (DX), artificial intelligence (AI), and machine learning (ML).

2023.01.05

推論技術:inference Technology検索技術:Search Technology機械学習:Machine Learning

Protected: Application of Neural Networks to Reinforcement Learning (2) Basic Framework Implementation

Implementation of a basic framework for reinforcement learning with neural networks utilized for digital transformation, artificial intelligence and machine learning tasks (TensorBoard, Image tab, graphical, real-time, progress check, wrapper for env. Observer, Trainer, Logger, Agent, Experience Replay, episode, action probability, policy, Epsilon-Greedy method, python)

2023.01.04

アルゴリズム:Algorithms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