Using Artificial Intelligence in Chemistry and Biology: A Practical Guide
Features
Summary
Possessing great potential power for gathering and managing data in chemistry, biology, and other sciences, Artificial Intelligence (AI) methods are prompting increased exploration into the most effective areas for implementation. A comprehensive resource documenting the current state-of-the-science and future directions of the field is required to furnish the working experimental scientist and newcomer alike with the background necessary to utilize these methods.
In response to the growing interest in the potential scientific applications of AI, Using Artificial Intelligence in Chemistry and Biology explains in a lucid, straightforward manner how these methods are used by scientists and what can be accomplished with them. Designed for those with no prior knowledge of AI, computer science, or programming, this book efficiently and quickly takes you to the point at which meaningful scientific applications can be investigated. The approach throughout is practical and direct, employing figures and illustrations to add clarity and humor to the topics at hand.
Unique in scope, addressing the needs of scientists across a range of disciplines, this book provides both a broad overview and a detailed introduction to each of the techniques discussed. Chapters include an introduction to artificial intelligence, artificial neural networks, self-organizing maps, growing cell structures, evolutionary algorithms, cellular automata, expert systems, fuzzy logic, learning classifier systems, and evolvable developmental systems. The book also comes with a CD containing a complete version of the EJS software with which most of the calculations were accomplished.
Encouraging a broader application of AI methods, this seminal work gives software designers a clearer picture of how scientists use AI and how to address those needs, and provides chemists, biologists, physicists, and others with the tools to increase the speed and efficiency of their work.
Table of Contents
Artificial Intelligence
What Is Artificial Intelligence?
Classification
The Practical Use of Artificial Intelligence Methods
Organization of the Text
Artificial Neural Networks
Introduction
Human Learning
Computer Learning
The Components of an Artificial Neural Network
Training
More Complex Problems
Layered Networks
Training a Layered Network: Backpropagation
Learning Rate
Momentum
Practical Issues
Traps and Remedies
Applications
Where Do I Go Now?
Problems
Self-Organizing Maps
Introduction
Measuring Similarity
Using a Self-Organizing Map
Components in a Self-Organizing Map
Network Architecture
Learning
Adjustable Parameters in the SOM
Practical Issues
Drawbacks of the Self-Organizing Map
Applications
Where Do I Go Now?
Problems
Growing Cell Structures
Introduction
Growing Cell Structures
Training and Evolving a Growing Cell Structure
Growing the Network
Removing Superfluous Cells
Advantages of the Growing Cell Structure
Applications
Where Do I Go Now?
Problems
Evolutionary Algorithms
Introduction
The Evolution of Solutions
Components in a Genetic Algorithm
Representation of a Solution in the Genetic Algorithm
Operation of the Genetic Algorithm
Evolution
When Do We Stop?
Further Selection and Crossover Strategies
Encoding
Repairing String Damage
Fine Tuning
Traps
Other Evolutionary Algorithms
Applications
Where Do I Go Now?
Problems
Cellular Automata
Introduction
Principles of Cellular Automata
Components of a Cellular Automata Model
Theoretical Applications
Practical Considerations
Extensions to the Model: Excited States
Lattice Gases
Applications
Where Do I Go Now?
Problems
Expert Systems
Introduction
An Interaction with a Simple Expert System
Applicability of Expert Systems
Goals of an Expert System
The Components of an Expert System
Inference Engine
Explanation and Limits to Knowledge
Case-Based Reasoning
An Expert System for All?
Expert System Shells
Can I Build an Expert System?
Applications
Where Do I Go Now?
Problems
Fuzzy Logic
Introduction
Crisp Sets
Fuzzy Sets
Calculating Membership Values
Membership Functions
Is Membership the Same as Probability?
Hedges
How Does a Fuzzy Logic System Work?
Application of Fuzzy Rules
Applications
Where Do I Go Now?
Problems
Learning Classifier Systems
Introduction
A Basic Classifier System
How a Classifier System Works
Properties of Classifiers
Learning Classifier System
Applications
Where Do I Go Now?
Problems
Evolvable Developmental Systems, N. Kharma
Introduction and Motivation
Relationship between Evolution and Development
Production Rules and the Evolution of Digital Circuits
Developmental Procedure
Cellular Growth and the Evolution of Functions
Description of Sample Problem
Summary
Future Challenges and Epilogue
