BI2BI17-Biologically Inspired Computing

Module Provider: School of Biological Sciences
Number of credits: 10 [5 ECTS credits]
Level:5
Terms in which taught: Autumn term module
Pre-requisites: BI1MA17 Mathematics
Non-modular pre-requisites:
Co-requisites:
Modules excluded:
Current from: 2021/2

Module Convenor: Prof Slawomir Nasuto
Email: s.j.nasuto@reading.ac.uk

Type of module:

Summary module description:

In spite of the advances in computing technology naturally occurring systems are still surprising us with the spectrum of complex behaviours they exhibit - pattern recognition, ability to self-repair, robustness to perturbations or noise, and adaptability in face of dynamic and often unpredictable environment. Seemingly simple tasks for natural systems offer state of the art challenges for traditional computation.

Such ability of dealing with complex information has inspired number of researchers to pursue novel computational methods inspired by biological solutions to what seem to be computational problems.

This module covers the theory and implementation of a number of computational systems inspired by biology, including brain inspired artificial neural networks, evolutionary algorithms, swarm intelligence methods based on social organisms, computing instantiated in molecules and cells and biologically inspired pattern formation systems.

Aims:

The module aims to provide basic introduction to foundations of computing as a theoretical framework enabling researcher to describe systems, artificial and natural, that deal with information. It will describe in detail modes of computation inspired by functionality of selected biological systems, namely artificial neural networks, evolutionary algorithms, swarm intelligence, cellular and DNA computing and biological pattern formation.

Assessable learning outcomes:

By the end of the module the student should be able to understand the basic concepts related to information, and computation and also evaluate their limitations in light of the processes and operations performed in biological systems. They will be familiar with the types of nonconventional computing systems inspired by biology and will understand in what context and how they can be applied to 'real-world' problems.

Additional outcomes:

Outline content:

Overview of the fundamentals of computing will be the starting point of the module. Various biologically inspired techniques will be described, for some their implementation is provided, and suitable applications discussed. Techniques examined are grouped by their biological inspiration (and mode of computation they offer): Artificial Neural Network architectures will be mostly focussing on the supervised methods selected from Single and Multi- Layer Perceptrons and associated learning method s; Radial Basis Function Networks; Self Organising Maps, Associative and Recurrent Networks. Algorithms inspired by natural evolution will include Genetic Algorithms and Evolutionary Programming. Swarm intelligence techniques will include Particle Swarm Optimisation, Ant Algorithms and Stochastic Diffusion Search. Methods inspired by cellular biology will be selected from membrane computing, DNA computing and amorphous computing and immune systems. Biologically inspired pattern formation methods will be selected from techniques including Lindenmeyer systems, Cellular Automata and Reaction Diffusion systems.

Brief description of teaching and learning methods:

The module comprises 2Ìýlectures per week.