微分積分:Calculus

オンライン学習

Protected: Advanced Online Learning (2) Distributed Parallel Processing(Parallelized mini-batch stochastic gradient method, IPM, BSP, SSP)

Distributed parallel processing of online learning (parallelized mini-batch stochastic gradient method, IPM, BSP, SSP) to efficiently process large scale data for digital transformation , artificial intelligence , and machine learning tasks.
微分積分:Calculus

Machine Learning Professional Series “Online Machine Learning” Reading Memo

Online learning reference books used for digital transformation , artificial intelligence , and machine learning tasks such as sequential processing of large-scale data.
オンライン学習

Protected: Advanced online learning (1) High accuracy Approach (Perceptron, PA, PA-I, PA-II, CW, AROW, SCW)

Introduction to various methods for improving the accuracy of online learning for digital transformation , artificial intelligence and machine learning tasks (Perceptron, PA, CW, AROW, SCW)
オンライン学習

Protected: Fundamentals of Online Learning Stochastic Gradient Descent – Application to Perceptron, SVM, and Logistic Regression

Online learning applications to the perceptron, SVM, and logistic regression for digital transformation , artificial intelligence , and machine learning tasks.
オンライン学習

Online learning and online prediction

Online learning is a sequential machine learning technique used in digital transformation , artificial intelligence , and machine learning tasks, and online prediction combines these techniques with decision-making problems.
データベース技術:DataBase Technology

Protected: Instance recognition and retrieval (2) General image retrieval

Search optimization using tree structure, hashing, sequential quantization, spectral hashing, k-means hashing, etc. for digital transformation and artificial intelligence tasks, and evaluation using mAP and recall@R.
微分積分:Calculus

Protected: Topic models – maximum likelihood estimation, variational Bayesian estimation, estimation by Gibbs sampling

Maximum likelihood, variational Bayesian, and Gibbs sampling estimation of topic models for digital transformation , artificial intelligence , and natural language processing tasks.
グラフ理論

Protected: Tensor decomposition – CP decomposition and Tucker decomposition

Processing of higher-order relational data and tensors using CP decomposition and Tucker decomposition for digital transformation and artificial intelligence tasks.
微分積分:Calculus

Protected: Estimating the number of topics in a topic model – Dirichlet process, Chinese restaurant process, stick-folding process

A topic model using Dirichlet process, Chinese restaurant process, and stick-folding process for digital transformation and artificial intelligence tasks.
微分積分:Calculus

Protected: Application of Topic Models to Information Other Than Documents – Application to Image Data and Graph Data (Stochastic Block Model, Mixed Member Probabilistic Block Model)

Topic models for image and graph data using stochastic block models for digital transformation and artificial intelligence tasks.
タイトルとURLをコピーしました