Kedziora D. AutonoML. Towards an Integrated Framework for Autonomous ML 2024

Download this torrent!

Kedziora D. AutonoML. Towards an Integrated Framework for Autonomous ML 2024

Category: Other
Total size: 7.32 MB
Added: 2025-03-10 23:39:03

Share ratio: 11 seeders, 2 leechers
Info Hash: 74C856F4CDC477B3B7E0DDE35AF9EDFC18FB81B6
Last updated: 10.2 hours ago

Textbook in PDF format Over the last decade, the long-running endeavour to automate high-level processes in machine learning (ML) has risen to mainstream prominence. Beyond this, an even loftier goal is the pursuit of autonomy, which describes the capability of the system to independently adjust an ML solution over a lifetime of changing contexts. This monograph provides an expansive perspective on what constitutes an automated/autonomous ML system. In doing so, the authors survey developments in hyperparameter optimisation, multicomponent models, neural architecture search, automated feature engineering, meta-learning, multi-level ensembling, dynamic adaptation, multi-objective evaluation, resource constraints, flexible user involvement, and the principles of generalisation. Furthermore, they develop a conceptual framework throughout to illustrate one possible way of fusing high-level mechanisms into an autonomous ML system. This monograph lays the groundwork for students and researchers to understand the factors limiting architectural integration, without which the field of automated ML risks stifling both its technical advantages and general uptake. Introduction Machine Learning Basics Algorithm Selection and Hyperparameter Optimisation Multi-component Pipelines Neural Architecture Search Automated Feature Engineering Meta-knowledge Ensembles and Bundled Pipelines Persistence and Adaptation Definitions of Model Quality Resource Management User Interactivity Towards General Applicability Discussion Conclusions