Books for machine learning people which are not books about machine learning

The fields of machine learning and data mining have become very narrow in the last five years or so. These are some books I recommend to remind people that the phenomena we group under these terms are actually much broader, richer and more fascinating than the few types we study.

Self-Organization in Biological Systems


Publisher: The synchronized flashing of fireflies at night. The spiraling patterns of an aggregating slime mold. The anastomosing network of army-ant trails. The coordinated movements of a school of fish. Researchers are finding in such patterns–phenomena that have fascinated naturalists for centuries–a fertile new approach to understanding biological systems: the study of self-organization. This book, a primer on self-organization in biological systems for students and other enthusiasts, introduces readers to the basic concepts and tools for studying self-organization and then examines numerous examples of self-organization in the natural world.

My comments: This is one of the best books on adaptation/learning/self-organization that I’ve seen. How individual entities may be simple but communities of them may be complex.

Thoughtless Acts? Observations on Intuitive Design


Publisher: People unconsciously perform ultraordinary actions every day, from throwing a jacket over a chair back to claim the seat, or placing something in the teeth when all hands are full. These “thoughtless acts” reveal the subtle but crucial ways people behave in a world not always perfectly tailored to their needs. Thoughtless Acts? is a collection of dozens of (often humorous) snapshots capturing such fleeting adaptations and minor exploitations.

My comments: This is actually an art/design book, and unlikely to be picked up by a machine learning person. But it documents ways in which humans adapt to their environments. Think of it almost as a human counterpart to the self-organization book above.

The Computational Beauty of Nature


Publisher: Gary William Flake develops in depth the simple idea that recurrent rules can produce rich and complicated behaviors. Distinguishing “agents” (e.g., molecules, cells, animals, and species) from their interactions (e.g., chemical reactions, immune system responses, sexual reproduction, and evolution), Flake argues that it is the computational properties of interactions that account for much of what we think of as “beautiful” and “interesting.” From this basic thesis, Flake explores what he considers to be today’s four most interesting computational topics: fractals, chaos, complex systems, and adaptation.

My comments: Probably the best book on chaos and complexity I’ve ever seen.

Sync: The Emerging Science of Spontaneous Order


Publisher: At once elegant and riveting, Sync tells the story of the dawn of a new science. Steven Strogatz, a leading mathematician in the fields of chaos and complexity theory, explains how enormous systems can synchronize themselves, from the electrons in a superconductor to the pacemaker cells in our hearts. He shows that although these phenomena might seem unrelated on the surface, at a deeper level there is a connection, forged by the unifying power of mathematics.

Silence on the Wire


Publisher: There are many ways that a potential attacker can intercept information, or learn more about the sender, as the information travels over a network. Silence on the Wire uncovers these silent attacks so that system administrators can defend against them, as well as better understand and monitor their systems.

My comments: This is purportedly a book about security, but it’s not really a security book. Machine learning people should think of it as a rich set of case studies about how apparently hidden information can be recovered and mined.

How Buildings Learn: What Happens After They’re Built


Publisher: All buildings are forced to adapt over time because of physical deterioration, changing surroundings and the life within–yet very few buildings adapt gracefully, according to Brand. Houses, he notes, respond to families’ tastes, ideas, annoyance and growth; and institutional buildings change with expensive reluctance and delay; while commercial structures have to adapt quickly because of intense competitive pressures.