courseraПрограммирование

Advanced Machine Learning and its Applications

Курс от University of Glasgow

Средний≈ 24.4 чАнглийский

О курсе

The third course introduces advanced machine learning techniques and their applications. This course is built on the Applied AI Foundations Specialization, which introduced the fundamentals of machine learning, and Course 1, which developed LLM-empowered Python programming skills for AI. In this course, advanced data preprocessing, machine learning outcome evaluation, neural network design and optimization, deep learning, and generative artificial intelligence are introduced. Since these techniques underpin essential modern AI systems in science and engineering, after completing this course, you will be able to develop, evaluate, and deploy advanced AI solutions using Python and LLM tools, providing a solid foundation for tackling real-world problems across a wide range of scientific and engineering domains.

Программа курса

5 модулей · 109 учебных материалов

01Advanced Data Preprocessing: Feature Selection and Dimension Reduction26 материалов

Welcome

Welcome to Advanced Machine Learning and its ApplicationsВидео Course Sample CertificateЧтение Specialisation Sample CertificateЧтение Connect with UofG OnlineЧтение

Module 7: Introduction

Учитесь у экспертов

Bo Liu

Professor

Xin Ma

Introduction to Advanced Data PreprocessingВидео

02Evaluating Machine Learning Outcomes22 материалов

Module 8 Introduction

Introduction to Machine Learning EvaluationВидео

Module 8-1: Fundamentals of Outcome Evaluation in Machine Learning

Introduction to Machine Learning EvaluationВидео PPT Lecture Slides - Evaluation FundamentalsЧтение

Module 8-2: Fundamentals and Traditional Methods of Outcome Evaluation

Holdout and Validation MethodsВидео PPT Lecture Slides - Traditional EvaluationЧтение

Module 8-3: Fundamentals and Methods of Evaluation for Sequential Data

Evaluating Sequential DataВидео PPT Lecture Slides - Sequential Data EvaluationЧтение

Module 8-4: Fundamentals and Methods of Evaluation for Unstable Model

Evaluating Unstable ModelsВидео PPT Lecture Slides - Unstable Model EvaluationЧтение

Module 8-5: Fundamentals and Methods of Evaluation for Data-Imbalance and Cost-Sensitive Problems

Evaluating Imbalanced DataВидео PPT Lecture Slides - Imbalanced Learning EvaluationЧтение

Module 8-6: Fundamentals and Hypothesis Testing Methods of Evaluation for Model Comparison and Statistical Testing

Model Comparison IssuesВидео PPT Lecture Slides - Model ComparisonЧтение

Module 8-7: Multiple Comparison Correction Methods of Evaluation for Model Comparison and Statistical Testing

Multiple Comparison ProblemsВидео PPT Lecture Slides - Multiple Comparison CorrectionЧтение

Module 8-8: Case Study

Case Study 1 - Application Cases of Outcome EvaluationВидео Case Study 2 - Cost Sensitive Evaluation of Credit Scorecard ModelsВидео PPT Lecture Slides - Application Case StudiesЧтение

Module 8-9: Dialogue

Designing a Reliable Machine Learning Evaluation StrategyDIALOGUE

Module 8-10: Quiz

Module 8 QuizЗадание

Module 8-11: Assignment

Module 8 Practice AssignmentЛабораторная

Module 8-12: Summary

Module 8 RecapВидео

Advanced Machine Learning and its Applications

О курсе

Навыки, которые вы освоите

Программа курса

Welcome

Module 7: Introduction

Учитесь у экспертов

Bo Liu

Xin Ma

Module 7-1: Fundamentals of Data Preprocessing and Anomalous Data Processing

Module 7-2: Fundamentals and Traditional Methods of Data Preprocessing

Module 7-3: Fundamentals and Filtering Methods for Feature Selection

Module 7-4: Wrapper Methods for Feature Selection

Module 7-5: Embedded Methods for Feature Selection

Module 7-6: Fundamentals and Linear Methods for Dimensionality Reduction

Module 7-7: Non-Linear Methods for Dimensionality Reduction

Module 7-8: Case Study

Module 7-9: Dialogue

Module 7-10: Quiz

Module 7-11: Assignment

Module 7-12: Summary

Module 8 Introduction

Module 8-1: Fundamentals of Outcome Evaluation in Machine Learning

Module 8-2: Fundamentals and Traditional Methods of Outcome Evaluation

Module 8-3: Fundamentals and Methods of Evaluation for Sequential Data

Module 8-4: Fundamentals and Methods of Evaluation for Unstable Model

Module 8-5: Fundamentals and Methods of Evaluation for Data-Imbalance and Cost-Sensitive Problems

Module 8-6: Fundamentals and Hypothesis Testing Methods of Evaluation for Model Comparison and Statistical Testing

Module 8-7: Multiple Comparison Correction Methods of Evaluation for Model Comparison and Statistical Testing

Module 8-8: Case Study

Module 8-9: Dialogue

Module 8-10: Quiz

Module 8-11: Assignment

Module 8-12: Summary

Module 9 Introduction

Module 9-1: Fundamentals of Neural Networks

Module 9-2: Traditional Methods of Neural Network Design and Tuning

Module 9-3: Adaptive Optimizer and Learning Rate Scheduling in Neural Networks

Module 9-4: Normalization Layers in Neural Networks

Module 9-5: Regularization Strategies for Mitigating Overfitting in Neural Networks

Module 9-6: Augmentation Methods for Mitigating Overfitting in Neural Networks

Module 9-7: Case Study

Module 9-8: Dialogue

Module 9-9: Quiz

Module 9-10: Assignment

Module 9-11: Summary

Module 10 Introduction

Module 10-1: Fundamentals of Deep Learning

Module 10-2: Fundamentals of Convolutional Neural Networks

Module 10-3: Typical Convolutional Neural Networks

Module 10-4: Fundamentals of Recurrent Neural Networks

Module 10-5: Typical Recurrent Neural Networks

Module 10-6: Fundamentals of Attention Mechanism

Module 10-7: Case Study

Module 10-8: Dialogue

Module 10-9: Quiz

Module 10-10: Assignment

Module 10-11: Summary

Module 11 Introduction

Module 11-1: Fundamentals of Generative AI

Module 11-2: Traditional Generative Models in Machine Learning

Module 11-3: Variational AutoEncoders

Module 11-4: Normalization Flow-based Models

Module 11-5: Generative Adversarial Networks

Module 11-6: Diffusion Models

Module 11-7: Case Study

Module 11-8: Dialogue

Module 11-9: Quiz

Module 11-10: Assignment

Module 11-11: Summary