May 1, 2024
Updated November 6, 2026
25 minute read
Automated Machine Learning, or AutoML, represents a significant shift in the field of Artificial Intelligence and Machine Learning. At its core, AutoML aims to automate the time-consuming, iterative tasks of machine learning model development. This allows data scientists, analysts, and even developers with limited machine learning expertise to build and deploy models with greater efficiency and scale. Imagine being able to automatically select the best algorithm for your data, fine-tune its parameters, and prepare your data for analysis, all with minimal manual intervention. This is the promise of AutoML.
ql79yg|
Find a path to becoming a AutoML. Learn more at:
OpenCourser.com/topic/ql79yg/autom
Reading list
We've selected 17 books
that we think will supplement your
learning. Use these to
develop background knowledge, enrich your coursework, and gain a
deeper understanding of the topics covered in
AutoML.
The definitive academic treatise on automated machine learning, providing comprehensive mathematical treatment of Bayesian optimization, hyperparameter tuning, neural architecture search, and meta-learning algorithms.
Authored by the lead developers of AutoKeras, delivering an applied guide to automating model search, multi-modal tabular pipelines, and neural architecture search using Python and Keras-based frameworks.
Presents contemporary research on the technological emergence and industrial application of AutoML systems, exploring automated pipeline construction, ensemble selection, and performance optimization.
Provides hands-on implementation practice for machine learning automation, exploring randomized search, grid search, and custom tuning loops that form the algorithmic core of automated pipeline optimization.
Analyzes the systems architecture of production machine learning platforms, examining continuous retraining, automated feature validation, model tracking, and monitoring essential for resilient AutoML deployments.
Synthesizes architectural best practices for foundation model evaluation suites, automated test pipelines, and continuous deployment monitoring. Equips machine learning engineers to design resilient automated workflows around complex modern architectures.
Guides engineers through automating data preprocessing, feature selection, model training, and hyperparameter tuning using open-source libraries like Auto-sklearn, TPOT, and H2O AutoML.
Explores systematic hyperparameter optimization techniques in Python, covering grid search, random search, Bayesian methods, and Optuna integrations to maximize machine learning predictive performance.
Delivers academic depth on automated machine learning methodologies applied to multimedia domains, exploring multi-modal neural architecture search, cross-domain transfer, and meta-learning abstractions.
Investigates the engineering realities of running automated ML pipelines in production, addressing data drift detection, automated retraining loops, telemetry infrastructure, and continuous model validation.
Demonstrates how to build automated deep learning pipelines for image, text, and tabular data using AutoKeras, teaching practitioners how to discover optimal neural architectures with minimal manual intervention.
Provides cloud-native DevOps architectures for orchestrating automated machine learning lifecycles, integrating CI/CD triggers, model registry synchronization, and automated hyperparameter sweep workers.
Focuses on building and scaling enterprise automated machine learning pipelines on Microsoft Azure, covering automated feature engineering, model selection, explainable AI, and MLOps deployment workflows.
Covers cloud-native automated machine learning workflows on AWS, demonstrating how to leverage Amazon SageMaker Autopilot for automated feature processing, algorithm selection, and containerized deployment.
Details practical enterprise AutoML implementations using Azure Machine Learning SDK, teaching teams how to automate model training, interpret feature importances, and configure continuous delivery pipelines.
Presents practical MLOps engineering principles for building robust, scalable automated machine learning platforms, emphasizing code testing, reproducible pipelines, and maintainable data infrastructures.
Bridges strategic executive decision-making and algorithmic data science, exploring how business organizations evaluate AutoML deployment ROI, workforce upskilling, and governance risks across automated corporate workflows.
For more information about how these books relate to this course, visit:
OpenCourser.com/topic/ql79yg/autom
Save
