Ivan I. Garibay

The Proportional Genetic Algorithm: Gene Expression in a Genetic Algorithm

We introduce a genetic algorithm (GA) with a new representation method which we call the proportional GA (PGA). The PGA is a multi-character GA that relies on the existence or non-existence of genes to determine the information that is expressed. The information represented by a PGA individual depends only on what is present on the individual and not on the order in which it is present. As a result, the order of the encoded information is free to evolve in response factors other than the value of the solution, for example, in response to the identification and formation of building blocks. The PGA is also able to dynamically evolve the resolution of encoded information. In this paper, we describe our motivations for developing this representation and provide a detailed description of a PGA along with discussion of its benefits and drawbacks. We compare the behavior of a PGA with that of a canonical GA (CGA) and discuss conclusions and future work based on these preliminary studies.

The Modular Genetic Algorithm: Exploiting Regularities in the Problem Space

We introduce the modular genetic algorithm (MGA). The modular genetic algorithm is a search algorithm designed for a class of problems pervasive throughout nature and engineering: problems with modularity and regularity in their solutions. We hypothesize that genetic search algorithms with explicit mechanisms to exploit regularity and modularity on the problem space would not only outperform conventional genetic search, but also scale better for this problem class. In this paper we present experimental evidence in support of our hypothesis. In our experiments, we compare a limited version of the modular genetic algorithm with a canonical genetic algorithm (GA) applied to the checkerboard-pattern discovery problem for search spaces of sizes 232, 2128, and 2512. We observe that the MGA significantly outperforms the GA for high complexities. More importantly, while the performance of the GA drops 22.50% when the complexity of the problem increases, the MGA performance drops only 11.38%. These results indicate that the MGA has a strong scalability property for problems with regularity and modularity in their solutions.

Effects of Module Encapsulation in Repetitively Modular Genotypes on the Search Space

We introduce the concept of modularity-preserving representations. If a representation is modularity-preserving, the existence of modularity in the problem space is translated into a corresponding modularity in the search space. This kind of representation allows us to analyze the impact of modularity at the genomic level. We investigate the question of what constitutes a module at the genomic level of evolutionary search and provide a static analysis of how to identify good and bad modules based on their ability to reduce the search space, thus, biasing the search space towards a solution. We also prove, under a set of assumptions, that the systematic encapsulation of lower order modules into higher order modules does not change the size or bias of a search space and that this process produces a hierarchy of equivalent search spaces.

Intelligent automated control of life support systems using proportional representations

Effective automatic control of Advanced Life Support Systems (ALSS) is a crucial component of space exploration. An ALSS is a coupled dynamical system which can be extremely sensitive and difficult to predict. As a result, such systems can be difficult to control using deliberative and deterministic methods. We investigate the performance of two machine learning algorithms, a genetic algorithm (GA) and a stochastic hill-climber (SH), on the problem of learning how to control an ALSS, and compare the impact of two different types of problem representations on the performance of both algorithms. We perform experiments on three ALSS optimization problems using five strategies with multiple variations of a proportional representation for a total of 120 experiments. Results indicate that although a proportional representation can effectively boost GA performance, it does not necessarily have the same effect on other algorithms such as SH. Results also support previous conclusions that multivector control strategies are an effective method for control of coupled dynamical systems.

Emergence of genomic self-similarity in location independent representations

A key property for predicting the effectiveness of stochastic search techniques, including evolutionary algorithms, is the existence of a positive correlation between the form and the quality of candidate solutions. In this paper we show that when the ordering of genomic symbols in a genetic algorithm is completely independent of the fitness function and therefore free to evolve along with the candidate solutions it encodes, the resulting genomes self-organize into self-similar structures that favor this key stochastic search property.

On the performance effects of unbiased module encapsulation

A recent theoretical investigation of modular representations shows that certain modularizations can introduce a distance bias into a landscape. This was a static analysis, and empirical investigations were used to connect formal results to performance. Here we replace this experimentation with an introductory runtime analysis of performance. We study a base-line, unbiased modularization that makes use of a complete module set (CMS), with special focus on strings that grow logarithmically with the problem size. We learn that even unbiased modularizations can have profound effects on problem performance. Our (1+1) CMS-EA optimizes a generalized OneMax problem in Ω(n2) time, provably worse than a (1+1) EA. More generally, our (1+1) CMS-EA optimizes a particular class of concatenated functions in O(2lm k n) time, where lm is the length of module strings and k is the number of module positions, when the modularization is aligned with the problem separability. We compare our results to known results for traditional EAs, and develop new intuition about modular encapsulation. We observe that search in the CMS-EA is essentially conducted at two levels (intra- and extra-module) and use this observation to construct a module trap, requiring super-polynomial time for our CMS-EA and O(n ln n) for the analogous EA.

Transformation Networks: A study of how technological complexity impacts economic performance

Under a resource-based view of the firm, economic agents transform resources from one form into another. These transformations can be viewed as the application of technology. The relationships between the technologies present in an economy can be modeled by a transformation network. The size and structure of these networks can describe the “economic complexity” of a society. In this paper, we use an agent-based computational economics model to investigate how the density of a transformation network affects the economic performance of its underlying artificial economy, as measured by the GDP. Our results show that the mean and median GDP of this economy increases as the density of its transformation network increases; furthermore, the cause of this increase is related to the number and type of cycles and sinks in the network. Our results suggest that economies with a high degree of economic complexity perform better than simpler economies with lower economic complexity.

Dario Floreano and Claudio Mattiussi (eds): Bio-inspired artificial intelligence: theories, methods, and technologies

Traditionally artificial intelligence has been focused on attempting to replicate the cognitive abilities of the human brain. Alternative approaches to artificial intelligence take inspiration from a wider range of biological processes such as evolution, networks of neurons and learning. In recent decades there has been an explosion of new artificial intelligence methods inspired by even more biological processes, such as the immune system, colonies of ants, physical embodiment, development, coevolution, self-organization, and behavioral autonomy, to mention just a few. ‘‘Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies’’, by Dario Floreano and Claudio Mattiussi, is a systematic and comprehensive introduction to the emerging field that groups all these methods: biologically inspired artificial intelligence. As a result, it discusses biological and artificial systems that operate at a wide range of time and space scales, but manages to move fluently from slow evolutionary time, to life-time learning, to real time adaptation. On the space scale, it goes from individual cells and neurons, to multicellular organisms, and all the way to societies. I found this book notable for at least two reasons. First, it provides a coherent intellectual framework to organize all these computational developments by grounding them in their biological nature and in the pervasiveness of evolution throughout biology. Second, it provides a clear, wellwritten, comprehensive, and authoritative account of these developments in an educational format well suited for a classroom. The authors manage to do all of that in only 659 pages, a great accomplishment considering the scope and depth of this book. The book is organized in seven chapters: evolutionary systems, cellular systems, neural systems, developmental systems, immune systems, behavioral systems and collective systems. The chapters are not independent but meant to be read in order

On favoring positive correlations between form and quality of candidate solutions via the emergence of genomic self-similarity

A key property for the effectiveness of stochastic search techniques, including evolutionary algorithms, is the existence of a positive correlation between the form and the quality of candidate solutions. In this paper, we show that when the ordering of genomic symbols in a genetic algorithm is completely independent of the fitness function and therefore free to evolve along the candidate solutions it encodes, the resulting genomes self-organize into self-similar structures that favor this key stochastic search property.

Role of entrepreneurial support for networking in innovation ecosystems: an agent based approach

Entrepreneurial support organizations are among the most successful approaches for economic growth. There are multiple dimensions of entrepreneurial support activities such as resource provision, funding or networking support. In this paper, we present an approach for the assessment and analysis of entrepreneurial support for networking and its effects on global innovation ecosystems. The innovation ecosystem in our approach is modeled as a complex adaptive network by using an agent-based modeling methodology with a focus on entrepreneurial support organizations. A portion of the economic entities in this ecosystem is provided with entrepreneurial support of different types to assess their effects. The results highlight the positive impact of networking support on the innovation ecosystem.