The Shallow and the Deep: A biased introduction to neural networks and old school machine learning
Michael Biehl, University of Groningen
Copyright Year:
ISBN 13: 9789403430270
Publisher: University of Groningen Press
Language: English
Formats Available
Conditions of Use
Attribution-NonCommercial-ShareAlike
CC BY-NC-SA
Reviews
Reviewed by Reighanna Lynch, Academic Director, Trine University on 5/10/26
Overall, the textbook provides a strong introduction to machine learning concepts and applications. While the field continues to evolve rapidly, the text establishes a solid foundational understanding of key principles and methodologies. The book... read more
Reviewed by Reighanna Lynch, Academic Director, Trine University on 5/10/26
Comprehensiveness
Overall, the textbook provides a strong introduction to machine learning concepts and applications. While the field continues to evolve rapidly, the text establishes a solid foundational understanding of key principles and methodologies. The book would benefit from the inclusion of a glossary to support learners who are new to the terminology; however, the text does provide organized lists of algorithms and references to where they are discussed throughout the book. Additionally, the table of contents is clearly structured and easy to navigate.
Content Accuracy
The content is accurate, error-free, and unbiased.
Relevance/Longevity
Because machine learning is a continuously developing field, the content will require frequent updates to remain current and relevant. The material appears to be organized in a way that would allow for updates to be implemented with relative ease; however, the PDF format may present challenges when making revisions and distributing updated versions efficiently.
Clarity
The text is written clearly, especially for the intended audience.
Consistency
The text is consistent.
Modularity
The text is effectively organized into chapters and subsections, making it easy for instructors to assign specific readings or integrate portions of the material into different course modules. The content is presented in manageable sections, avoiding overly dense blocks of text that could reduce student engagement or readability.
Organization/Structure/Flow
The text is well-organized and presented well.
Interface
Overall, there were no major issues identified with the interface or visual presentation of the text, such as image distortion or formatting inconsistencies. However, accessibility remains a concern. PDF documents are not inherently accessible and require additional formatting and compatibility features to fully support all learners. In addition, some headings and page indicators are presented in all capital letters, which may create challenges for students using screen readers, as this formatting can interfere with proper text interpretation and readability.
Grammatical Errors
There were no visible grammatical errors.
Cultural Relevance
There was no culturally sensitive or offensive material.
CommentsI would not choose this text as an OER resource.
Table of Contents
- Preface
- From neurons to networks
- Learning from example data
- The Perceptron
- Beyond linear separability
- Feed-forward networks for regression and classification
- Distance-based classifiers
- Model evaluation and regularization
- Preprocessing and unsupervised learning
- Concluding quote
- Appendix A: Optimization
- List of figures
- List of algorithms
- Abbrev. and acronyms
- Bibliography
About the Book
The Shallow and the Deep is a collection of lecture notes that offers an accessible introduction to neural networks and machine learning in general. However, it was clear from the beginning that these notes would not be able to cover this rapidly changing and growing field in its entirety. The focus lies on classical machine learning techniques, with a bias towards classification and regression. Other learning paradigms and many recent developments in, for instance, Deep Learning are not addressed or only briefly touched upon.
Biehl argues that having a solid knowledge of the foundations of the field is essential, especially for anyone who wants to explore the world of machine learning with an ambition that goes beyond the application of some software package to some data set. Therefore, The Shallow and the Deep places emphasis on fundamental concepts and theoretical background. This also involves delving into the history and pre-history of neural networks, where the foundations for most of the recent developments were laid. These notes aim to demystify machine learning and neural networks without losing the appreciation for their impressive power and versatility.
About the Contributors
Author
Michael Biehl is Associate Professor of Computer Science at the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence of the University of Groningen, where he joined the Intelligent Systems group in 2003. He also holds an honorary Professorship of Machine Learning at the Center for Systems Modelling and Quantitative Biomedicine of the University of Birmingham, UK. His research focuses on the modelling and theoretical understanding of neural networks and machine learning in general. The development of efficient training algorithms for interpretable, transparent systems is a topic of particular interest. A variety of interdisciplinary collaborations concern practical applications of machine learning in the biomedical domain, in astronomy and other areas.