Similarly to past ALife and ECAL conferences, ALIFE 2018 will be composed of a number of sessions, whose topics will be determined by the submissions. However there will also be a number of special sessions, organised by members of the Artificial Life community to increase engagement in particular topics. These sessions share the same review system as the main conference tracks, and accepted submissions will be published in the proceedings.
The special sessions are listed below. To submit to a special session, follow the instructions for authors and select your session when prompted. Please feel free to contact the session organisers directly for more details about a session.
Special sessions are distinct from workshops, which are organised separately from the main conference. Workshops will be announced at a later date. (To propose a workshop, see the workshops page.)
List of Sessions (click for more details)
- ALife and Society: Transcending the artificial-natural divide
- Hybrid life: Approaches to integrate biological, artificial and cognitive systems
- Machine Learning in ALife
- Morphogenetic Engineering
ALife and Society: Transcending the artificial-natural divide
Organisers: Alex Penn and J. Mario Siqueiros
Details to be announced
Hybrid Life: Approaches to integrate biological, artificial and cognitive systems
Organisers: Manuel Baltieri (M.Baltieri@sussex.ac.uk), Keisuke Suzuki and Hiroyuki Iizuka
The main focus of ALife research is the study of natural systems with the goal of understanding what life is. More concretely, ALife defines ways to investigate processes that contribute to the formation and proliferation of living organisms. In this session we focus on three common approaches to tackle this investigation, proposing ways to integrate, extend and possibly improve them. More specifically we refer to: 1) the formalisation of the necessary properties for the definition of life, 2) the implementation of artificial agents, and 3) the study of the relation between life and cognition.
For this special session we propose to start from these well-established Alife methodologies, and extend them through:
- a unified formal language for the description and modelling of living, as well as artificial and cognitive systems, e.g. control theory, Bayesian inference, dynamical systems theory, etc.
- the exploration of biological creatures enhanced by artificial systems (or artificial systems augmented with organic parts) in order to investigate the boundaries between living and nonliving organisms, and
- the evaluation of coupled biological-artificial systems that could shed light on the importance of interactions among systems for the study of living and cognitive organisms.
This special sessions aims to invite contributions from the fields of psychology, computational neuroscience, HCI, theoretical biology, artificial intelligence, robotics and cognitive science to discuss current research on the formalisation, combination and interaction of artificial/living/cognitive systems from theoretical, modelling and implementational perspectives.
Potential topics include, but are not limited to:
- Formalisation of life and cognition (e.g. dynamical systems theory, stochastic optimal control, Bayesian inference, etc.)
- Cognitive robotics
- Life-mind continuity thesis
- Systems biology
- Origins-of-life theories with relationships to artificial and cognitive systems
- Animal-robot interaction
- Bio-inspired robotics
- Bio-integrated robotics
- Human-machine interaction
- Augmented cognition
- Sensory substitution
- Interactive evolutionary computation
- Artificial perception
Machine Learning in ALife
Organiser: Nicholas Guttenberg
In recent years, machine learning has moved past the pure optimization perspective into exploring more complex interacting modes of learning and behavior. For example, techniques involving multiple competing agents have been used to produce photorealistic images, perform negotiations at a super-human level of performance, and to master the game of Go. These techniques have brought machine learning closer to the mainstay of ALife research and present opportunities for both fields to benefit from each others’ expertise and insight.
In this session, we would like to invite submissions which introduce new ideas from machine learning that may be interesting for ALife research, discuss ALife work which makes use of machine learning techniques, or which discuss or interpret phenomena from machine learning systems in light of an ALife perspective.
Topics of interest include (but are not limited to)
- Using dynamical systems and complex systems theory to understand the dynamics of learning
- Relationships between evolution, reinforcement learning, and supervised learning
- ALife models using agents that learn
Multi-agent machine learning
- Adversarial dynamics in machine learning (generative adversarial networks and the like)
- Self-play and discovery
- Communication between agents
- Open-endedness and creativity in machine learning systems
- Learned motivations / intrinsic motivations
This special session aims to promote and expand Morphogenetic Engineering, a field of research exploring the artificial design and implementation of autonomous systems capable of developing complex, heterogeneous morphologies. Particular emphasis is set on the programmability and controllability of self-organization, properties that are often underappreciated in complex systems science–while, conversely, the benefits of self-organization are often underappreciated in engineering methodologies.
Traditional engineered products are generally made of a number of unique, heterogeneous components assembled in complicated but precise ways, and are intended to work deterministically following specifications given by their designers. By contrast, self-organization in natural complex systems (physical, biological, ecological, social) often emerges from the repetition of agents obeying identical rules under stochastic dynamics. These systems produce relatively regular patterns (spots, stripes, waves, trails, clusters, hubs, etc.) that can be characterized by a small number of statistical variables. They are random and/or shaped by boundary conditions, but do not exhibit an intrinsic architecture like engineered products do.
Salient exceptions, however, strikingly demonstrate the possibility of combining pure self-organization and elaborate architectures: biological development (the self-assembly of myriads of cells into the body plans and appendages of organisms) and insect constructions (the stigmergic collaboration of colonies of social insects toward large and complicated nests). These structures are composed of segments and parts arranged in very specific ways that resemble the products of human inventiveness. Yet, they entirely self-assemble in a decentralized fashion, under the control of genetic or behavioral rules stored in every agent.
How do these collectives (cells or insects) achieve such impressive morphogenetic tasks so reliably? Can we export their precise self-formation capabilities to engineered systems? What are principles and best practices for the design and engineering of such morphogenetic systems?
Topics of interest:
- New principles of morphogenesis in artificial systems
- Bio-inspiration from plant vs. animal development
- Programmability of self-organizing morphogenetic systems
- Indirect, decentralized control of morphogenetic systems
- Sensitivity to environmental/boundary conditions vs. endogenous drive
- Evolvability, by variations and selection, of morphogenetic systems
- Links with evolutionary computation, artificial embryogeny, “evo-devo” approaches
- Swarm-based approaches to morphogenetic systems
- Design techniques for morphogenetic engineering
- Causalities between micro and macro properties of morphogenetic systems
- Physical implementations
- Applications to real-world problems (swarm robots, synthetic biology, complex networks, etc.)
- Philosophical questions about morphogenetic engineering