AIC-305: Bio-Inspired Artificial Intelligence

Course Syllabus

Course Description

This competency explores a diverse range of algorithms designed to address complex, large-scale, or computationally intractable problems by drawing inspiration from natural and biological processes. The primary focus is on understanding how adaptive mechanisms observed in nature—such as evolution, self-organization, and collective behavior—can be translated into computational models for optimization and problem-solving.

A key area of study involves genetic algorithms (GAs), which emulate the principles of natural selection and genetic evolution to iteratively evolve high-quality solutions. These algorithms operate through processes such as selection, crossover, and mutation, allowing populations of candidate solutions to converge toward an optimal or near-optimal outcome over successive generations.

In addition to genetic algorithms, the competency encompasses swarm intelligence techniques, which are inspired by the decentralized and cooperative behaviors of social organisms like ants, bees, and birds. Representative examples include Ant Colony Optimization (ACO), which models pheromone-based communication for pathfinding and routing problems, and Particle Swarm Optimization (PSO), which simulates the movement and social interactions of particles in search of optimal solutions within a multidimensional space.

Through the study of these bio-inspired computational paradigms, learners gain insight into how distributed intelligence, adaptability, and stochastic exploration can be leveraged to tackle optimization, classification, and scheduling problems that are otherwise difficult to solve using traditional deterministic algorithms. The competency therefore bridges the gap between natural systems and artificial computation, emphasizing the role of emergent behavior and probabilistic reasoning in modern problem-solving approaches.

General Information

Competency Code AIC-305
Competency Name Bio-Inspired AI
Competency Credits 4
Competency Duration 7 Weeks (~7.5 Hours Per Week = 52 Hours in Total)
Instructor Dr. Charnon Pattiyanon <charnon@cmkl.ac.th>

Assessing Skills

  1. [AIC-305:00010] Explain the core ideas that underlie bio-inspired AI - Successful students must be able to .
  2. [AIC-305:00020] Create a simple GA system to solve a problem - Successful students must be able to .
  3. [SEC-201:00030] Create a simple system that uses a swarm intelligence method to solve a problem - Successful students must be able to .

Class Schedule and Topics

Week Lecture Topic
Week 1 Lecture 1: Introduction to Bio-Inspired AI
Lecture 2: Problem Formulation
  • Inspiration from Nature
  • Introduction to Computational Intelligence
  • Self-Organization
  • Computational Intelligence Paradigms
  • Problem Formulation
[Lecture 1 (PDF)] | [Lecture 2 (PDF)]

Assessment Project Announcement
Week 2 Lecture 3: Evolutionary Computation
  • Gene Representation
  • Genotype and Phenotype
  • Generic Evolutionary Algorithm
[Lecture 3 (PDF)]
Week 3 Assessment Project 1 Evolutionary Computation Presentation
Week 4 Lecture 4: Swarm Intelligence
  • Collective Behaviors
  • Ant Colony Optimization
  • Particle Swarm Optimization
[Lecture 4 (PDF)]
Week 5 Assessment Project 2 Swarm Intelligence Presentation
Week 6 Lecture 5: Artificial Immune System
  • Biological Immune System
  • Three Lines of Body Defenses
  • Antigen and Antibody
  • T Cell and B Cell
  • Basic AIS Algorithm
[Lecture 5 (PDF)]
Week 7 Assessment Project 3 Artificial Immune System Presentation

Assessment and Submission Guideline

This competency requires each student group to submit five deliverables, including:

  1. A List of Team Members: This list should include each member’s first name, last name, nickname, and email address.
  2. Problem Statement: This deliverable should provide a concise paragraph describing the problem that can be addressed using bio-inspired AI algorithms.
  3. Three Presentation Decks: These decks are to be used during your presentation sessions and must be submitted one day before the presentation date.

Grading Rubric

Presentation Grading Rubric

The presentation will be equivalent to 100% of your final score or 300 points out of 300 points (from three assessing skills). Each of the presentation will be equivalent to 100 points. Some parts will be graded as a group performance, while others will be graded individually. The following rubric will be used for grading the presentation.

  • (70%) Correctness: Points will be awarded to each team member based on their understanding of the content presented. This criterion also includes how well each individual responds to questions.
  • (20%) Presentation: Full points will be awarded to groups that deliver their presentations smoothly, demonstrating thorough preparation and adequate rehearsal.
  • (10%) Application: Full points will be awarded to groups that appropriately apply bio-inspired AI algorithms to the selected problem.