Representation Learning

Beschreibung

This monograph addresses advances in representation learning, a cutting-edge research area of machine learning. Representation learning refers to modern data transformation techniques that convert data of different modalities and complexity, including texts, graphs, and relations, into compact tabular representations, which effectively capture their semantic properties and relations. The monograph focuses on (i) propositionalization approaches, established in relational learning and inductive logic programming, and (ii) embedding approaches, which have gained popularity with recent advances in deep learning. The authors establish a unifying perspective on representation learning techniques developed in these various areas of modern data science, enabling the reader to understand the common underlying principles and to gain insight using selected examples and sample Python code. The monograph should be of interest to a wide audience, ranging from data scientists, machine learning researchers and students to developers, software engineers and industrial researchers interested in hands-on AI solutions.
This monograph addresses advances in representation learning, a cutting-edge research area of machine learning. Representation learning refers to modern data transformation techniques that convert data of different modalities and complexity, including texts, graphs, and relations, into compact tabular representations, which effectively capture their semantic properties and relations. The monograph focuses on (i) propositionalization approaches, established in relational learning and inductive logic programming, and (ii) embedding approaches, which have gained popularity with recent advances in deep learning. The authors establish a unifying perspective on representation learning techniques developed in these various areas of modern data science, enabling the reader to understand the common underlying principles and to gain insight using selected examples and sample Python code. The monograph should be of interest to a wide audience, ranging from data scientists, machine learning researchers and students to developers, software engineers and industrial researchers interested in hands-on AI solutions.
Representation learning for cutting-edge machine learning – the benefit is a unifying approach to data fusion and transformation into compact tabular format used in standard learners and modern deep neural classifiers Coverage of tables, relations, texts, networks and ontologies – the benefit is a unified approach to handling heterogeneous data, enabling data scientists to step out of their isolated machine learning silos used in their routine practice Open science approach with hands-on examples – the benefit is the methodology and code reuse, as well as replicability with demo use cases

Autor*in

Nada Lavrač

Themen in »Representation Learning«

embeddings data fusion heterogeneous data mining relational data mining feature construction propositionalization texts networks ontologies semantic data mining information networks open science deep learning machine learning relational learning

Stimmen zu »Representation Learning«

Details

Link teilen