A Brief Introduction to Swarm Intelligence
Credit: E. Grant.
Neuroscience and intelligence
Brain-to-body mass ratio
Credit: Wikimedia Commons, Nhobgood.
Conceptual bridge between biological and artificial intelligence.
AI-hard or AI-complete
-360 Aristotle described the syllogism, a method of formal, mechanical thought.
1206 Al-Jazari created a programmable orchestra of mechanical human beings
1600 René Descartes proposed that bodies of animals are nothing more than complex machines
1642 Blaise Pascal invented the mechanical calculator, the first digital calculating machine
1769 Wolfgang von Kempelen built and toured with his chess-playing automaton, The Turk
1913 Bertrand Russell and Alfred North Whitehead published Principia Mathematica, which revolutionized formal logic
1931 Kurt Gödel, father of theoretical computer science
1950 Alan Turing proposes the Turing Test as a measure of machine intelligence
1997 The Deep Blue chess machine (IBM) defeats the (then) world chess champion, Garry Kasparov
2005 Blue Brain is born, a project to simulate the brain at molecular detail
2011 IBM’s Watson computer defeated television game show Jeopardy! champions Rutter and Jennings
2011 Apple’s Siri, Google’s Google Now and Microsoft’s Cortana are smartphone apps that use natural language to answer questions, make recommendations and perform actions
Search and optimization
Search algorithm, Mathematical optimization and Evolutionary computation
Logic programming and Automated reasoning
Probabilistic methods for uncertain reasoning
Bayesian network, Hidden Markov model, Kalman filter, Decision theory and Utility theory
Classifiers and statistical learning methods
Classifier (mathematics), Statistical classification and Machine learning
Artificial neural network and Connectionism
Control theory Languages
In the radio series and the first novel, a group of hyper-intelligent pan-dimensional beings demand to learn the Answer to the Ultimate Question of Life, The Universe, and Everything from the supercomputer, Deep Thought, specially built for this purpose. It takes Deep Thought 71⁄2 million years to compute and check the answer, which turns out to be 42. Deep Thought points out that the answer seems meaningless because the beings who instructed it never actually knew what the Question was. The Ultimate Question: What do you get if you multiply six by nine? The Answer: 613 × 913 = 4213
Swarm intelligence (SI) is the collective behavior of decentralized, self-organized systems, natural or artificial. Introduced by Gerardo Beni and Jing Wang in 1989, in the context of cellular robotic systems. Examples in natural systems of SI: • Ant colonies • Bird flocking • Animal herding • Bacterial growth • Fish schooling • Microbial intelligence Inspiration from Nature 1. Social Insects • Natural Navigation • Natural Clustering • Natural construction 2. Foraging 3. Flocking
Nature Inspired Search Techniques
Particle swarm optimization. Simulating social behaviour.
Credit: M. E. H. Pedersen.
Ant colony optimization. A probabilistic technique in metaheuristic optimizations.
Credit: Wikimedia Commons.
Artificial bee colony algorithm. Intelligent foraging behaviour.
MR brain image classification Face pose estimation
Differential evolution. A method that optimizes a problem by iteratively trying to improve a candidate solution.
The bees algorithm. A population-based search algorithm.
Optimisation of classifiers/Clustering systems
Artificial immune systems. A class of computationally intelligent systems. Adaptive systems.
Bat algorithm. A metaheuristic optimization algorithm.
Classifications of gene expression data
Glowworm swarm optimization. The algorithm makes the agents glow at intensities approximately proportional to the function value being optimized.
Gravitational search algorithm. Based on the law of gravity and the notion of mass interactions.
Self-propelled particles. Predict robust emergent behaviours occur in swarms independent of the type of animal that is in the swarm.
Stochastic diffusion search. An agent-based probabilistic global search and optimization technique best suited to problems where the objective function can be decomposed into multiple independent partial-functions.
A comprehensive mathematical framework.
Multi-swarm optimization. Use of multiple sub-swarms instead of one (standard) swarm.
Multi-swarm system effectively combines components from Particle swarm optimization, Estimation of distribution algorithm, and Differential evolution into a multiswarm hybrid.