Taras Kowaliw

Promoting Creative Design in Interactive Evolutionary Computation

We use a new measure of creativity as a guide in an interactive evolutionary art task and tie the results to natural language usage of the term “creative.” Following previous work, we explore a tractable definition of creativity, one emphasizing the novelty of systems, and its addition to an interactive application. We next introduce a generative ecosystemic art system, EvoEco, an agent-based pixel-level means of generating images. EvoEco is used as a component of an online survey which asks users to evolve a pleasing image and then rank the success of the process and its output. Evolutionary search is augmented with the creativity measure, and compared with control groups augmented with either random search or a measure of phenotypic distance. We show that users consistently rate the creativity measure-enhanced version as more “creative” and “novel” than other search techniques. We further derive additional insights into appropriate forms of genetic representation and pattern space-traversal in an interactive evolutionary algorithm.

Evolving novel image features using Genetic Programming-based image transforms

In this paper, we use Genetic Programming (GP) to define a set of transforms on the space of greyscale images. The motivation is to allow an evolutionary algorithm means of transforming a set of image patterns into a more classifiable form. To this end, we introduce the notion of a Transform-based Evolvable Feature (TEF), a moment value extracted from a GP-transformed image, used in a classification task. Unlike many previous approaches, the TEF allows the whole image space to be searched and augmented. TEFs are instantiated through Cartesian Genetic Programming, and applied to a medical image classification task, that of detecting muscular dystrophy-indicating inclusions in cell images. It is shown that the inclusion of a single TEF allows for significantly superior classification relative to predefined features alone.

Image Processing and CGP

In this chapter, we will present three applications in which CGP can automatically generate novel image processing algorithms that compare to or exceed the best known conventional solutions. The applications fall into the areas of image preprocessing and classification.

Embryomorphic Engineering: Emergent innovation through evolutionary development

Embryomorphic Engineering, a particular instance of Morphogenetic Engineering, takes its inspiration directly from biological development to create new robotic, software or network architectures by decentralized self-assembly of elementary agents. At its core, it combines three key principles of multicellular embryogenesis: chemical gradient diffusion (providing positional information to the agents), gene regulatory networks (triggering their differentiation into types, thus patterning), and cell division or aggregation (creating structural constraints, thus reshaping). This chapter illustrates the potential of Embryomorphic Engineering in different spaces: 2D/3D physical swarms, which can find applications in collective robotics, synthetic biology or nanotechnology; and \(n\)D graph topologies, which can find applications in distributed software and peer-to-peer techno-social networks. In all cases, the specific genotype shared by all the agents makes the phenotype’s complex architecture and function modular, programmable and reproducible.

Brainless Bodies: Controlling the Development and Behavior of Multicellular Animats by Gene Regulation and Diffusive Signals

We present a model of parallel co-evolution of development and motion control in soft-bodied, multicellular animats without neural networks. Development is guided by an artificial gene regulatory network (GRN), with real-valued expression levels, contained in every cell. Embryos develop within a simulated physics environment and are converted into animat structures by connecting neighboring cells through elastic springs. Outer cells, which form the external envelope, are affected by drag forces in a fluid-like environment. Both the developmental program and locomotion controller are encoded into a single genomic sequence, which consists of regulatory regions and genes expressed into transcription factors and morphogens. We apply a genetic algorithm to evolve individuals able to swim in the simulated fluid, where the fitness depends on distance traveled during the evaluation phase. We obtain various emergent morphologies and types of locomotion, some of them showing the use of rudimentary appendages. An analysis of the selected evolved controllers is provided.

Augmenting artificial development with local fitness

In biology, the importance of environmental feedback to the process of embryogenesis is well understood. In this paper we explore the introduction of a local fitness to an artificial developmental system, providing an artificial analogue to the natural phenomenon. First, we define a highly simplified model of vasculogenesis, an environment-based toy problem in which we can evaluate our strategies. Since the use of a global fitness function for local feedback is likely too computationally expensive, we introduce the notion of a neighbourhood-based “local fitness” function. This local fitness serves as an environmental-feedback guide for the developmental system. The result is a developmental analogue of guided hill-climbing, one which significantly improves the performance of an artificial embryogeny in the evolution of a simplified vascular system. We further evaluate our model in a collection of randomly generated two-dimensional geometries, and show that inclusion of local fitness helps allay some of the problem difficulty in irregular environments. In the process, we also introduce a novel and systematic means of generating bounded, connected two-dimensional geometries.

Developmental Design of Synthetic Bacterial Architectures by Morphogenetic Engineering

Synthetic biology is an emerging scientific field that promotes the standardized manufacturing of biological components without natural equivalents. Its goal is to create artificial living systems that can meet various needs in health care or energy domains. While most works are focused on the individual bacterium as a chemical reactor, our project, SynBioTIC, addresses a novel and more complex challenge: shape engineering; that is, the redesign of natural morphogenesis toward a new kind of developmental 3D printing. Potential applications include organ growth, natural computing in biocircuits, or future vegetal houses. To create in silico multicellular organisms that exhibit specific shapes, we construe their development as an iterative process combining fundamental collective phenomena such as homeostasis, patterning, segmentation, and limb growth. Our numerical experiments rely on the existing Escherichia coli simulator Gro, a physicochemical computation platform offering reaction-diffusion and collision dynamics solvers. The synthetic bioware of our model executes a set of rules, or genome, in each cell. Cells can differentiate into several predefined types associated with specific actions (divide, emit signal, detect signal, die). Transitions between types are triggered by conditions involving internal and external sensors that detect various protein levels inside and around the cell. Indirect communication between bacteria is relayed by morphogen diffusion and the mechanical constraints of 2D packing. Starting from a single bacterium, the overall architecture emerges in a purely endogenous fashion through a series of developmental stages, inlcuding proliferation, differentiation, morphogen diffusion, and synchronization. The genome can be parametrized to control the growth and features of appendages individually. As exemplified by the L and T shapes that we obtain, certain precursor cells can be inhibited while others can create limbs of varying size (divergence of the homology). Such morphogenetic phenotypes open the way to more complex shapes made of a recursive array of core bodies and limbs and, most importantly, to an evolutionary developmental exploration of unplanned functional forms.

Controlling development and chemotaxis of soft-bodied multicellular animats with the same gene regulatory network

The ability to actively forage for resources is one of the defining properties of animals, and can be seen as a form of minimal cognition. In this paper we model soft-bodied robots, or “animats”, which are able to swim in a simulated twodimensional fluid environment toward food particles emitting a diffusive chemical signal. Both the multicellular development and behaviour of the animats are controlled by a gene regulatory network (GRN), which is encoded in a linear genome. Coupled with the simulated physics, the activity of the GRN affects cell divisions and cell movements during development, as well as the expansion and contraction of filaments connecting the cells in the swimming adult body. The global motion that emerges from the dynamics of the animat relies on the spring-like filaments and drag forces created by the fluid. Our study shows that it is possible to evolve the animat’s genome (through mutations, duplications and deletions) to achieve directional motion in this environment. It also suggests that a “minimally cognitive” behaviour of this kind can emerge without a central control or nervous system.

An interactive electronic art system based on artificial ecosystemics

In this paper, we explore a generative art system designed to promote the creation of a diverse range of aesthetically pleasing images. We introduce our system, EvoEco, an agent-based pixel-level means of generating images based on artificial ecosystems. This art system is driven by interactive evolutionary computation, and further augmented using special measures to promote the diversity of the individuals. Following previous work, we explore a tractable definition of creativity and its addition to this interactive search. EvoEco was released online, and used by forty-one anonymous users to generate artwork. Here we present some of the discovered results.

Growing Adaptive Machines

The pursuit of artificial intelligence has been a highly active domain of research for decades, yielding exciting scientific insights and productive new technologies. In terms of generating intelligence, however, this pursuit has yielded only limited success. This book explores the hypothesis that adaptive growth is a means of moving forward. By emulating the biological process of development, we can incorporate desirable characteristics of natural neural systems into engineered designs and thus move closer towards the creation of brain-like systems. The particular focus is on how to design artificial neural networks for engineering tasks. The book consists of contributions from 18 researchers, ranging from detailed reviews of recent domains by senior scientists, to exciting new contributions representing the state of the art in machine learning research. The book begins with broad overviews of artificial neurogenesis and bio-inspired machine learning, suitable both as an introduction to the domains and as a reference for experts. Several contributions provide perspectives and future hypotheses on recent highly successful trains of research, including deep learning, the Hyper NEAT model of developmental neural network design, and a simulation of the visual cortex. Other contributions cover recent advances in the design of bio-inspired artificial neural networks, including the creation of machines for classification, the behavioural control of virtual agents, the design of virtual multi-component robots and morphologies and the creation of flexible intelligence. Throughout, the contributors share their vast expertise on the means and benefits of creating brain-like machines. This book is appropriate for advanced students and practitioners of artificial intelligence and machine learning.