Natural Computation and Applications Xin Yao http www

Natural Computation and Applications Xin Yao http: //www. cs. bham. ac. uk/~xin Natural Computation Group School of Computer Science The University of Birmingham UK

Frustration About Computers § § § § Brittle Non-adaptive Doesn’t learn Hopeless in dealing with noisy and inaccurate information Doesn’t do the homework for me although I told it that I want a mark over 70% Never grow up Slow …

The Solution § What did we do when we had problems as a kid? Who do we normally turn to? §Ask our mother!

Motivation: Mother Nature

Nature Inspired Computation

Characteristics of Nature Inspired Computation § Flexible: applicable to different problems § Robust: can deal with noise and uncertainty § Adaptive: environments can deal with dynamic § Autonomous: without human intervention § Decentralised: authority without a central

Natural Inspired Computation § Evolutionary computation § Neural computation § Molecular computation § Quantum computation § Ecological computation § Chemical computation §…

Overview of Methods

Natural Computation Methods: Selected Examples Evolutionary Algorithms Artificial Neural Networks Agent-based techniques Ant colony / Swarm techniques Inspired by the biological process of evolution Inspired by the function of neurons in the brain Inspired by human social interaction Inspired by the behaviour of social

Evolutionary Algorithms Selection Parents Recombination Population Mutation Replacement Offspring

Artificial Neural Networks § Simplified model of a brain § Consist of inputs, processing and outputs § All layers joined by artificial neurons § Fault tolerant § Noise resistant § Can learn and generalise § Good at perception tasks

Agent-based Techniques § Multiple independent agents follow individual strategies § Macro-level behaviour develops § Useful for modelling trading strategies § Can simulate competitive markets § Dynamically optimised scheduling

Ant Colony Optimisation

Selected Examples

Container Packing § How to put as many boxes of different sizes into containers in order to minimise space wastage

Swarm intelligence for Animation Flocking can be simulated in computers • Flocking uses rapid shortrange communication • Behaviour governed by mutual avoidance, alignment and affinity. • Simple rules generate complex behaviour

Channel Allocation Inspired by Fruit Flies § Fruitflies have an insensitive exoskeleton peppered with sensors formed from short bristles attached to nerve cells. It is important that the bristles are more or less evenly spread out across the surface of the fly. In particular it is undesirable to have two bristles right next to each other. § The correct pattern is formed during the fly's development by interactions among its cells. The individual cells "argue" with each other by secreting protein signals, and perceiving the signals of their neighbours. The cells are autonomous, each running its own "algorithm" using information from its local environment. Each cell sends a signal to its neighbours; at the same time it listens for such a signal from its neighbours.

Constrained Dynamic Routing § Dynamic call routing in telecommunication networks • Finding optimal routes for salting trucks • Evolutionary algorithms: Robust, efficient and can be used for hard, dynamic problems for which there is little domain knowledge

Time Series Prediction § Telecommunicatio ns traffic flow prediction § Blue-green algae activity prediction in fresh water lakes § Energy consumption prediction

Recognition and Classification § Object recognition § Medical diagnosis § Credit card assessment § Fraud detection § Vehicle tracking § Subscriber churn prediction

Creative Technologies § Natural computation techniques can be used effectively in the creative industry for graphics, images, music, games, etc. § Highly effective at exploring the huge space of possible artefacts § Boids § Karl Sims’s artificial creatures

Creative Technologies: Evolutionary Art § Evolutionary art from Andrew Rowbottom § Genetic art by Peter Kleiweg § Organic art by William Latham

Summary § Evolutionary computation is part of natural computation § Evolutionary computation can be used in optimisation, data mining and creative design. § Evolutionary computation are particularly good at solving complex real –world problems where very little domain knowledge is available. § Evolutionary computation complements the existing methods.

Further Information § http: //www. cs. bham. ac. uk/research/NC/ (research group in the School) § http: //www. cs. bham. ac. uk/study/postgrad uate-taught/msc-nc/ (MSc in Natural Computation) § http: //www. evonet. polytechnique. fr/CIRC US 2/ (Evolutionary Computation Education Center - (EC)² ) § http: //ieee-nns. org/pubs/tec/ (IEEE Transactions on Evolutionary Computation)