数学:Mathematics

アルゴリズム:Algorithms

Protected: Unconstrained optimization for continuous optimization in machine learning

Unconstrained Optimization for Continuous Optimization in Machine Learning for Digital Transformation, Artificial Intelligence, and Machine Learning tasks machine epsilon, stopping conditions without scaling, stopping conditions with scaling, Taylor's theorem, stopping conditions for optimization algorithms, Hesse matrix
アルゴリズム:Algorithms

Protected: Unsupervised Learning with Gaussian Processes (1)Overview and Algorithm of Gaussian Process Latent Variable Models

Overview and algorithms of unsupervised learning using Gaussian Process Latent Variable Models GPLVM, an application of probabilistic generative models used in digital transformation, artificial intelligence, and machine learning, Bayesian Gaussian Process Latent Variable Models ,Bayesian GPLVM
アルゴリズム:Algorithms

Protected: Implementation of model-free reinforcement learning in python (2) Monte Carlo and TD methods

Python implementations of model-free reinforcement learning such as Monte Carlo and TD methods Q-Learning, Value-based methods, Monte Carlo methods, neural nets, Epsilon-Greedy methods, TD(lambda) methods, Muli-step Learning, Rainbow, A3C/A2C, DDPG, APE-X DDPG, Muli-step Learning) Epsilon-Greedy method, TD(λ) method, Muli-step Learning, Rainbow, A3C/A2C, DDPG, APE-X DQN
グラフ理論

Protected: Information Geometry of Positive Definite Matrices (1) Introduction of dual geometric structure

Introduction of dual geometric structures as information geometry for positive definite matrices utilized in digital transformation, artificial intelligence, and machine learning tasks (Riemannian metric, tangent vector space, semi-positive definite programming problem, self-equilibrium, Levi-Civita connection, Riemannian geometry, geodesics, Euclidean geometry, ∇-geodesics, tangent vector, tensor quantity, dual flatness, positive definite matrix set)
バンディッド問題

Protected: Fundamentals of Stochastic Bandid Problems

Basics of stochastic bandid problems utilized in digital transformation, artificial intelligence, and machine learning tasks (large deviation principle and examples in Bernoulli distribution, Chernoff-Heffding inequality, Sanov's theorem, Heffding inequality, Kullback-Leibler divergence, probability mass function, hem probability, probability approximation by central limit theorem).
微分積分:Calculus

Protected: Fundamentals of Convex Analysis as a Basic Matter for Sequential Optimization in Machine Learning

Basics of convex analysis as a fundamental matter of continuous optimization utilized in digital transformation, artificial intelligence, and machine learning tasks subgradient, subdifferential, conjugate function, closed truly convex function, conjugate function, strongly convex function, closed truly convex function, upper and lower bounds on function values, Hesse matrix, epigraph, Taylor's theorem, relative interior, Ahuynh envelope, continuity, convex envelope, convex function, convex set
アルゴリズム:Algorithms

Protected: Basic Framework of Statistical Mathematics Theory

Basic framework of statistical mathematics theory used in digital transformation, artificial intelligence, and machine learning tasks regularization, approximation and estimation errors, Höfding's inequality, prediction discriminant error, statistical consistency, learning algorithms, performance evaluation, ROC curves, AUC, Bayes rules, Bayes error, prediction loss, empirical loss
アルゴリズム:Algorithms

Protected: Supervised learning and regularization

Overview of supervised learning regression, discriminant and regularization ridge function, L1 regularization, bridge regularization, elastic net regularization, SCAD, group regularization, generalized concatenated regularization, trace norm regularization as the basis of machine learning optimization methods used for digital transformation, artificial intelligence and machine learning tasks
アルゴリズム:Algorithms

Protected: Spatial statistics of Gaussian processes, with application to Bayesian optimization

Spatial statistics of Gaussian processes as an application of stochastic generative models used in digital transformation, artificial intelligence, and machine learning tasks, and tools ARD, Matern kernelsfor Bayesian optimization GPyOpt and GPFlow and GPyTorch
アルゴリズム:Algorithms

Protected: Implementation of model-free reinforcement learning in python (1) epsilon-greedy method

Implementation in python of the epsilon-Greedy method, a model-free reinforcement learning method for use in digital transformation, artificial intelligence, and machine learning tasks, multi-armed bandit
タイトルとURLをコピーしました