-- Non-Darwinian Evolutionary Computation for Optimization and Design
-- Software Engineering with Computational Intelligence

Evolutionary computation was originally inspired by the Darwinian model of evolution that proceeds via the repetition of two major steps, one that involves introducing innovation into the current population of individuals, and the second, natural selection, that creates a new parent population from the generated new individuals. In the conventional methods of evolutionary computation, innovation is typically done through random or semi-random mutations and/or recombinations. The evolutionary process is not guided by any reasoning method or "intelligent agent," and therefore tends not to be very efficient.
 
More recently, several new directions in evolutionary computation sprang to life such as Cultural Algorithms, Estimation of Distribution Algorithms, Memetic Algorithms, and Learnable Evolution Model, all of which can be called Non-Darwinian, because they use non-conventional methods of introducing innovation and/or involve a combination of different modes of operation. This track aims at bringing together researchers conducting theoretical and experimental research on various forms of such Non-Darwinian evolutionary computation. Topics of interest to this track include, but are not limited to:

• Cultural Algorithms
• Estimation of Distribution Algorithms
• Learnable Evolution Model
• Memetic Algorithms
• Real-world Applications and Comparative studies
• Theoretical Aspects of non-Darwinian Evolutionary Computation

The constantly evolving technological infrastructure presents a daunting challenge of the development and assurance of software systems with increasing size and complexity. Software engineers and project managers are striving to address various problems observed during the different phases of the software development life cycle. However, though related research has seen the development of some important and useful software engineering paradigms, their technology-transfer on a larger scale has been extremely gradual. The recent emergence of computational intelligence techniques in software engineering has opened doors for exploiting the currently developed and mature techniques of fuzzy logic, artificial neural networks, case-based reasoning, machine learning, knowledge-based systems, evolutionary computing, and expert systems.
The Special Track on Software Engineering with Computational Intelligence will focus on the current research trends in the fusion of the computational intelligence and software engineering domains. The topics of particular interest to the special track include but are not limited to:

• Fuzzy Logic
• Artificial Neural Networks
• Case-Based Reasoning
• Knowledge- and Rule-Based Systems
• Evolutionary Computing
• Hybrid Intelligent Systems
• Machine Learning and Data Mining
• Software Requirements and Specifications
• Software Cost and Effort Estimation
• Formal Methods
• Software Measures and Soft Computing
• Software Testing
• Software Verification and Validation
• Software Quality and Reliability Estimation
• Quality of Software Measurement Data
• Context-aware Software Systems
• Autonomic Systems
• Web-based Systems