Local editorial preview · InnoWorks Press
InnoWorks Press
Artificial Computational Intelligence front cover

INNOWORKS PRESS · REVIEW EDITION

Computing and systems

Artificial Computational Intelligence

Hybrid reasoning and adaptive systems

Combining several methods creates new interfaces as well as new possibilities. Does each component earn its place? This manuscript uses constrained scheduling to connect representations, simple baselines, optimisation, evolutionary search, fuzzy rules and adaptation over time. It keeps comparative evidence and reproducibility close to the architecture. Artificial Computational Intelligence is the book's local organising label for hybrid methods; the title does not establish a new scientific discipline. The reader is invited to examine the contribution of each method before accepting the complexity of their combination.

Manuscript and companion under editorial and technical review. This local preview does not announce publication or sale.

Inside the book

A route through the ideas

Who it is for

Advanced students and researchers exploring hybrid computational methods, constrained optimisation and the design of comparative studies.

  1. Define the term and the claim
  2. Represent knowledge and observations
  3. Establish simple baselines
  4. Optimisation with constraints
  5. Evolutionary and population methods
  6. Fuzzy systems and readable rules
  7. Learning components in a larger system
  8. Combining methods without hiding failure
  9. Adaptation over time
  10. Evidence for comparative claims
  11. Human review and responsibility
  12. A reproducible hybrid system study

Chapter titles follow the current review manuscript. Final pagination and edition details remain subject to review.

From the opening chapter

Begin with an idea

A workshop has five jobs to finish and two machines that can do them. Someone proposes an intelligent scheduler with learning, fuzzy rules and evolutionary search. Each phrase names a potentially useful method. None yet tells the foreman which job will finish sooner, what information the scheduler will require, or why the extra machinery deserves to remain.

We will begin with that small discomfort. A system diagram can become more impressive while its claim becomes harder to test. The remedy is not hostility to complexity. It is to give each component a question precise enough that a simpler alternative could answer it too. If the simpler alternative does equally well at lower cost, the comparison has taught us something useful.

Computational intelligence already includes established work on neural networks, evolutionary methods, fuzzy systems and their combinations [1]. In this book, Artificial Computational Intelligence is a local organising name for investigating hybrid designs. Naming the framework does not establish a new discipline, a conscious machine or a universal advantage. Its value must be found in explanations and results that survive comparison.

Beyond the page

Make the idea work

Read. Predict. Experiment. Explain.

Move between the explanation and a working investigation. Each chapter provides a question, inspectable code or a model, and practice that asks you to explain the result.

  1. Read the argument before running the calculation.
  2. Change an input or assumption and inspect the result.
  3. Explain what the model supports, and what it leaves open.
Open the chapter companion →

Chapter QR codes connect the print proof to these materials. The online edition is being prepared locally; public links require a verified release.

About the author

Akash Chatake

Akash Shivadas Chatake writes and teaches across machine learning, artificial intelligence, computation and mathematics. His books connect an explanation with a question the reader can investigate, moving between the mathematical idea and the practical work it makes possible.

Explore the author’s work ↗