scholarly journals Integrative Biological Simulation, Neuropsychology, and AI Safety

2018 ◽  
Author(s):  
Gopal P. Sarma ◽  
Adam Safron ◽  
Nick J. Hay
Keyword(s):  
Data Model ◽  
Sensorimotor Integration ◽  
Fruit Fly ◽  
Nematode Caenorhabditis Elegans ◽  
Biologically Inspired ◽  
Goal Structures ◽  
System Architectures ◽  
Intellectual Traditions ◽  
Biological Simulation ◽  
Ai Safety

We describe a biologically-inspired research agenda with parallel tracks aimed at AI and AI safety. The bottom-up component consists of building a sequence of biophysically realistic simulations of simple organisms such as the nematode Caenorhabditis elegans, the fruit fly Drosophila melanogaster, and the zebrafish Danio rerio to serve as platforms for research into AI algorithms and system architectures. The top-down component consists of an approach to value alignment that grounds AI goal structures in neuropsychology, broadly considered. Our belief is that parallel pursuit of these tracks will inform the development of value-aligned AI systems that have been inspired by embodied organisms with sensorimotor integration. An important set of side benefits is that the research trajectories we describe here are grounded in long-standing intellectual traditions within existing research communities and funding structures. In addition, these research programs overlap with significant contemporary themes in the biological and psychological sciences such as data/model integration and reproducibility.

scholarly journals Integrative biological simulation, neuropsychology, and AI safety

2019 ◽  
Author(s):  
Gopal P Sarma ◽  
Adam Safron ◽  
Nick J. Hay
Keyword(s):  
Data Model ◽  
Research Agenda ◽  
Sensorimotor Integration ◽  
Fruit Fly ◽  
Biologically Inspired ◽  
Goal Structures ◽  
System Architectures ◽  
Intellectual Traditions ◽  
Biological Simulation ◽  
Ai Safety

We describe a biologically-inspired research agenda with parallel tracks aimed at AI and AI safety. The bottom-up component consists of building a sequence of biophysically realistic simulations of simple organisms such as the nematode Caenorhabditis elegans, the fruit fly Drosophila melanogaster, and the zebrafish Danio rerio to serve as platforms for research into AI algorithms and system architectures. The top-down component consists of an approach to value alignment that grounds AI goal structures in neuropsychology, broadly considered. Our belief is that parallel pursuit of these tracks will inform the development of value-aligned AI systems that have been inspired by embodied organisms with sensorimotor integration. An important set of side benefits is that the research trajectories we describe here are grounded in long-standing intellectual traditions within existing research communities and funding structures. In addition, these research programs overlap with significant contemporary themes in the biological and psychological sciences such as data/model integration and reproducibility.

scholarly journals Integrative biological simulation, neuropsychology, and AI safety

2019 ◽  
Author(s):  
Gopal P Sarma ◽  
Adam Safron ◽  
Nick J. Hay
Keyword(s):  
Data Model ◽  
Research Agenda ◽  
Sensorimotor Integration ◽  
Fruit Fly ◽  
Biologically Inspired ◽  
Goal Structures ◽  
System Architectures ◽  
Intellectual Traditions ◽  
Biological Simulation ◽  
Ai Safety

We describe a biologically-inspired research agenda with parallel tracks aimed at AI and AI safety. The bottom-up component consists of building a sequence of biophysically realistic simulations of simple organisms such as the nematode Caenorhabditis elegans, the fruit fly Drosophila melanogaster, and the zebrafish Danio rerio to serve as platforms for research into AI algorithms and system architectures. The top-down component consists of an approach to value alignment that grounds AI goal structures in neuropsychology, broadly considered. Our belief is that parallel pursuit of these tracks will inform the development of value-aligned AI systems that have been inspired by embodied organisms with sensorimotor integration. An important set of side benefits is that the research trajectories we describe here are grounded in long-standing intellectual traditions within existing research communities and funding structures. In addition, these research programs overlap with significant contemporary themes in the biological and psychological sciences such as data/model integration and reproducibility.

scholarly journals Integrative biological simulation, neuropsychology, and AI safety

2018 ◽  
Author(s):  
Gopal P Sarma ◽  
Adam Safron ◽  
Nick J. Hay
Keyword(s):  
Data Model ◽  
Research Agenda ◽  
Sensorimotor Integration ◽  
Fruit Fly ◽  
Biologically Inspired ◽  
Goal Structures ◽  
System Architectures ◽  
Intellectual Traditions ◽  
Biological Simulation ◽  
Ai Safety

We propose a biologically-inspired research agenda with parallel tracks aimed at AI and AI safety. The bottom-up component consists of building a sequence of biophysically realistic simulations of simple organisms such as the nematode Caenorhabditis elegans, the fruit fly Drosophila melanogaster, and the zebrafish Danio rerio to serve as platforms for research into AI algorithms and system architectures. The top-down component consists of an approach to value alignment that grounds AI goal structures in neuropsychology. Our belief is that parallel pursuit of these tracks will inform the development of value-aligned AI systems that have been inspired by embodied organisms with sensorimotor integration. An important set of side benefits is that the research trajectories we describe here are grounded in long-standing intellectual traditions within existing research communities and funding structures. In addition, these research programs overlap with significant contemporary themes in the biological and psychological sciences such as data/model integration and reproducibility.

Molecular Mechanisms of Sexually Dimorphic Nervous System Patterning in Flies and Worms

2021 ◽  
Vol 37 (1) ◽  
pp. 519-547
Author(s):  
Stephen F. Goodwin ◽  
Oliver Hobert
Keyword(s):  
Molecular Mechanisms ◽  
Fruit Fly ◽  
Model Systems ◽  
Recent Analysis ◽  
Sexually Dimorphic ◽  
Nematode Caenorhabditis Elegans ◽  
Animal Kingdom ◽  
Detailed Understanding ◽  
Sexual Dimorphisms ◽  
Functional Differences

Male and female brains display anatomical and functional differences. Such differences are observed in species across the animal kingdom, including humans, but have been particularly well-studied in two classic animal model systems, the fruit fly Drosophila melanogaster and the nematode Caenorhabditis elegans. Here we summarize recent advances in understanding how the worm and fly brain acquire sexually dimorphic features during development. We highlight the advantages of each system, illustrating how the precise anatomical delineation of sexual dimorphisms in worms has enabled recent analysis into how these dimorphisms become specified during development, and how focusing on sexually dimorphic neurons in the fly has enabled an increasingly detailed understanding of sex-specific behaviors.

Emphasizing Mechanical Feedback in Bio-Inspired Design and Education

2011 ◽  
Author(s):  
Justin Seipel
Keyword(s):  
Feedback Control ◽  
The Body ◽  
The Self ◽  
Biological Research ◽  
Biologically Inspired ◽  
System Architectures ◽  
Mechanical Control ◽  
Conventional View ◽  
Neural Feedback ◽  
Mechanical Feedback

Mechanical feedback in nature is a useful concept proposed by many researchers in different areas of biological research. The concept, at its core, is simply the idea that many mechanical processes in biology effectively act to assist in the self-stabilization of tasks, and therefore, serve functionally as a first level of feedback control. However, due to a conventional view of the nervous system as the ‘controller’ of the body, it has historically been assumed that the control of tasks does not critically depend on the self-stability properties of the mechanical (musculo-skeletal) system. More recent biological research has provided many examples that show neural feedback alone is not sufficient to control many tasks. This forces us to reframe our conventional view of feedback control in neuro-mechanical systems, and by extension, provide a more appropriate perspective when designing biologically-inspired system architectures. Here two ways of diagraming neuro-mechanical control are compared to understand whether one may be more helpful in framing neuro-mechanical control problems and biologically-inspired system design for engineering practitioners and students. This work, when developed further, is expected to provide new pedagogical frameworks for teaching neuromechanics, motor-control, and biologically-inspired methods of control.

Sign in / Sign up

Export Citation Format

Share Document